han 4.3.2 re-focuses the code-overview skill around why code exists and adds an adversarial accuracy-validation pass to it (han-coding 2.3.1), and adds two how-to guides plus the research backing one of them to the suite documentation. han-core, han-planning, han-github, han-reporting, han-feedback, han-atlassian, and han-linear are unchanged.

What's Changed

• How to change a plan by @mxriverlynn in #87
• How to: accelerate understanding of unfamiliar code by @mxriverlynn in #88
• Code overview: answering "why" as the most important aspect by @mxriverlynn in #89

han v4.3.2

The suite-level work is documentation. Two how-to guides were added: docs/how-to/revise-a-plan.md covers how to change a plan after the build has started, and docs/how-to/accelerate-understanding-of-unfamiliar-code.md covers getting up to speed on unfamiliar code. Both are surfaced in docs/how-to/README.md and the recipe list in the root README.md. docs/research/llm-accelerated-code-understanding.md was added as the research backing the understanding-acceleration guide. docs/how-to/plan-a-feature.md and docs/skills/README.md got one-line updates, and the research summary dropped a banned word for voice compliance. README.md also got a header fix for the Claude installation section. Contributed by @mxriverlynn in #87 and #88.

han-coding v2.3.1

The code-overview skill (han-coding/skills/code-overview/SKILL.md and han-coding/skills/code-overview/references/overview-template.md) was reworked in two ways.

First, the whole overview is now organized around one question: why does this code exist? The answer is the real problem the code solves or the goal it serves for the business or a user, never the technical mechanics. Code mode leads with a "Why it exists" section and PR mode with a "Why this change exists" section, and every following section (flow, context, where to start) is framed as serving that why. The skill's description frontmatter, its operating constraints, the Step 4 explorer dispatch, the Step 5 rendering order, and the per-section detail rule were all updated to put the why first. The Step 4 dispatch now asks explorers to gather evidence of why the code exists from commit messages, PR and issue intent, comments, naming, and tests, and to say so rather than invent a reason when the why is not stated. Where the why can only be inferred, the overview marks it as inferred and does not assert a business rationale the evidence does not support.

Second, Step 7 (renamed "Validate Accuracy, then Refine for Readability") now dispatches three agents in parallel instead of two: han-core:adversarial-validator joins han-core:information-architect and han-core:junior-developer. The validator re-reads the target, and the diff in PR mode, and challenges every material claim the overview makes, the stated why most of all, for grounding in the actual code and its intent, citing the file, line, or commit that disproves any unsupported, overstated, contradicted, or hallucinated claim. It validates the accuracy of the description only and does not judge the code's quality or raise findings about the code. Accuracy corrections take precedence over readability edits when the skill applies recommendations. docs/skills/han-coding/code-overview.md and docs/agents/han-core/adversarial-validator.md were updated to match, and the adversarial-validator agent doc now names /code-overview as a dispatcher. Contributed by @mxriverlynn in #89.

Full changelog: https://github.com/testdouble/han/blob/v4.3.2/CHANGELOG.md#v432
Full Changelog: v4.3.1...v4.3.2

han 4.3.1 removes the Claude-specific model overrides from the four planning skills so they run on hosts with their own model namespaces (han-planning 2.0.2), and clarifies the agent-model-selection guidance so the overrides are not reintroduced (han-plugin-builder 2.0.1). han-core, han-coding, han-github, han-reporting, han-feedback, han-atlassian, and han-linear are unchanged.

What's Changed

• Docs/sweep sizing and dispatch fixes by @mxriverlynn in #85
• Remove Claude-specific model overrides from planning skills (#78) by @mxriverlynn in #86

Issues closed

• Han Feedback: han-feedback (2026-06-17) (#78) — opened by @oppegard, fixed in #86 by @mxriverlynn

han v4.3.1

The suite-level work is documentation. The cost sections of the four planning long-form docs (docs/skills/han-planning/plan-a-feature.md, docs/skills/han-planning/plan-implementation.md, docs/skills/han-planning/plan-a-phased-build.md, docs/skills/han-planning/plan-work-items.md) were updated to match the model-override removal below. docs/research/issue-78-model-specifier-portability.md was added as the research backing that change. CLAUDE.md and CONTRIBUTING.md corrected the han-linear layout label and documented han-atlassian and han-linear in the contributor guide.

han-planning v2.0.2

The four planning skills (plan-a-feature, plan-implementation, plan-a-phased-build, plan-work-items) pinned every dispatched sub-agent to model: "sonnet". That tier name is Claude-specific and is not valid on hosts with their own model namespace, so the planning skills failed before useful work began. The blanket "all sub-agents run on sonnet" operating principle and all 11 per-dispatch model overrides across the four SKILL.md files were removed. Each dispatched agent now runs on its own frontmatter tier on Claude Code, or the host default elsewhere. This also restores the deliberate opus promotion of junior-developer, information-architect, and user-experience-designer that the overrides were silently undoing. Implements option O1 from docs/research/issue-78-model-specifier-portability.md. Contributed by @mxriverlynn in #86.

han-plugin-builder v2.0.1

The agent-model-selection.md guidance (han-plugin-builder/skills/guidance/references/agent-building-guidelines/agent-model-selection.md) now clarifies that the "always set model explicitly" rule scopes to agent definition files only, not to skill dispatch, so the planning-skill overrides are not reintroduced. Contributed by @mxriverlynn in #86.

Full changelog: https://github.com/testdouble/han/blob/v4.3.1/CHANGELOG.md#v431
Full Changelog: v4.3.0...v4.3.1

han 4.3.0 teaches the coding-standard skill to cite code by durable, greppable anchors instead of volatile file:line references (han-coding 2.3.0), and applies a one-line wording fix to gap-analysis (han-core 2.0.2). han-planning, han-github, han-reporting, han-feedback, han-atlassian, han-linear, and han-plugin-builder are unchanged.

What's Changed

• docs: align PR template checklist with the count-free index convention by @taminomara in #81
• docs: fix stale long-form doc paths after the plugin-rename reorg by @taminomara in #80
• feat: coding standard durable references by @taminomara in #79

Issues closed

• coding-standard skill generates standards that cite volatile codebase state, so produced standards go stale (#73) — opened by @taminomara, fixed in #79 by @taminomara; thanks to @mxriverlynn

han v4.3.0

The suite-level work is documentation and repo-root config. docs/agents/han-core/concurrency-analyst.md corrected its dispatch claims. docs/concepts.md, docs/quickstart.md, docs/skills/han-coding/coding-standard.md, docs/skills/han-reporting/stakeholder-summary.md, and docs/templates/coverage-rule.md got sizing-aware-list and count-free-index-convention fixes, plus stale long-form doc path corrections left over from the plugin-rename reorg (#80). .github/pull_request_template.md and CONTRIBUTING.md were aligned with the count-free index convention (#81). CLAUDE.md dropped CLAUDE.md itself from the list of places the doc-update skill needs to keep current. .claude-plugin/marketplace.json carries the per-plugin version syncs for this release.

han-coding v2.3.0

The coding-standard skill now generates standards that cite code by durable, greppable anchors instead of file:line references that go stale as the codebase moves. A new reference file han-coding/skills/coding-standard/references/durable-references.md holds the rule: numbered rules for deriving a greppable anchor (Rules 1 and 2, with an escalation path that flags a place for engineer review when it cannot be cleanly anchored), Rule 3 for writing "Applies To" as a membership criterion, and Rule 4 idioms for timeless phrasing.

In han-coding/skills/coding-standard/SKILL.md, the Step 4 han-core:codebase-explorer dispatch prompts now ask for a file path, a line range, and one or more greppable durable anchors per place (following Rules 1 and 2), and flag places that reach escalation for engineer review rather than returning an anchor. The standards/ADRs explorer asks for cross-references as a document path plus a stable section heading, and the merged context block gains a "Flagged candidates" bucket for places that could not be cleanly anchored. Step 6 reads and applies durable-references.md in its authoring mode throughout, writing "Applies To" as a membership criterion (Rule 3) and surfacing any flagged candidate with a recommended resolution instead of emitting a coarse or anchorless reference. The verification step adds a temporal-phrasing scan over the whole document, not just the citations, reframing temporal hits to the timeless property via the Rule 4 idioms and flagging anything that cannot be re-anchored. Index-file entry descriptions now follow Rule 3 as well. The output template han-coding/skills/coding-standard/references/template.md changed its Project-references bullet to pair a file path with a stable anchor. Contributed by @taminomara in #79.

han-core v2.0.2

The han-core/skills/gap-analysis/SKILL.md han-core:junior-developer actor-perspective sweep changed its trailing actor examples from "internal admins, auditors" to "internal services". Wording only, no behavior change.

Full changelog: https://github.com/testdouble/han/blob/v4.3.0/CHANGELOG.md#v430
Full Changelog: v4.2.0...v4.3.0

han 4.2.0 ships a new code-overview skill (han-coding 2.2.0) and a Confluence-publishing wrapper for it (han-atlassian 2.2.0), simplifies the /update-pr-description output (han-github 2.1.0), and adds a description cross-reference to /project-documentation (han-core 2.0.1). han-planning, han-reporting, han-feedback, han-linear, and han-plugin-builder are unchanged.

What's Changed

• New skill /han-coding:code-overview by @mxriverlynn in #83
• Simplify the update-pr-description skill's output by @mxriverlynn in #84

han v4.2.0

The suite-level work is documentation. New long-form docs docs/skills/han-coding/code-overview.md and docs/skills/han-atlassian/code-overview-to-confluence.md were added for the two new skills, and the code-overview feature specification and its artifacts were filed under docs/plans/code-overview/ (feature-specification.md, artifacts/decision-log.md, artifacts/team-findings.md). A docs sweep applied follow-up edits across docs/: docs/skills/README.md, docs/choosing-a-han-plugin.md, docs/sizing.md, the long-form agent docs for codebase-explorer, information-architect, and junior-developer, and the long-form docs for update-pr-description, code-review, project-documentation, and project-discovery. The top-level CLAUDE.md "When to use which doc" list was greatly reduced (25e05bf), and a docs fix corrected the han-atlassian dependency phrasing and project-discovery scope (dcd260f). .claude-plugin/marketplace.json carries the per-plugin version syncs for this release.

han-coding v2.2.0

New skill: code-overview

A new skill code-overview produces a progressive-disclosure, understand-now overview of unfamiliar code or a pull request's changes: what it does, how it flows, and where to start. It writes the overview to a scratch file and changes no code. Added in han-coding/skills/code-overview/SKILL.md with the output template in han-coding/skills/code-overview/references/overview-template.md. The overview output forbids PR statistics, and a follow-up added an intro paragraph, a readability pass, and PR screenshots. han-coding/skills/code-review/SKILL.md gained a cross-reference pointing to the new skill. Contributed by @mxriverlynn in #83.

han-atlassian v2.2.0

New skill: code-overview-to-confluence

A new skill code-overview-to-confluence runs the core code-overview skill to produce the overview, then publishes it to a user-specified Confluence location through the Atlassian MCP server. Added in han-atlassian/skills/code-overview-to-confluence/SKILL.md. The han-atlassian/.claude-plugin/plugin.json description was updated to list the new skill. Contributed by @mxriverlynn in #83.

han-github v2.1.0

Simplified /update-pr-description output

The update-pr-description skill's generated PR description is now capped at 2-5 short paragraphs. The Summary section is the bolded TL;DR sentence, Behavior changes is its own section, and "What to look at first" appears only when the PR has more than roughly 8-10 files with significant code changes. The "Files of interest", "Test scenario changes", and "How this was tested" sections were dropped, the separate test-applicability step was removed, and han-github/skills/update-pr-description/references/formatting-rules.md was deleted. references/template.md and references/template-conformance.md were reworked to match. This is a backward-compatible refinement of the same skill, not a new capability. Contributed by @mxriverlynn in #84.

han-core v2.0.1

The project-documentation skill description gained a cross-reference clarifying that it does not produce an ephemeral, understand-now overview of code or a PR, pointing to the new code-overview skill instead. Description text only, no behavior change.

Full changelog: https://github.com/testdouble/han/blob/v4.2.0/CHANGELOG.md#v420
Full Changelog: v4.1.0...v4.2.0

han 4.1.0 ships a new Confluence-publishing skill (han-atlassian 2.1.0) and teaches the /tdd skill to write a passing regression test when the work is a bug fix (han-coding 2.1.0), plus a description cross-reference fix to /plan-a-phased-build (han-planning 2.0.1). han-core, han-github, han-reporting, han-feedback, han-linear, and han-plugin-builder are unchanged.

What's Changed

• TDD Skill: Add failure characterization by @mxriverlynn in #76
• han-atlassian: add investigate-to-confluence skill by @mxriverlynn in #77

Issues closed

• tdd: error characterization tests assert the error is raised instead of asserting correct behavior that fails for the expected reason (#74) — opened by @mxriverlynn, fixed in #76 by @mxriverlynn
• han-atlassian: add an investigate-to-confluence skill that wraps investigate and publishes results to Confluence (#75) — opened by @mxriverlynn, fixed in #77 by @mxriverlynn

han v4.1.0

The suite-level work is documentation. A docs sweep applied follow-up edits across docs/: the long-form agent docs for data-engineer, devops-engineer, on-call-engineer, and user-experience-designer (sibling-agent reciprocity, which agents dispatch them, and operator-facing detail), docs/concepts.md, docs/choosing-a-han-plugin.md, docs/skills/README.md, and the long-form docs for issue-triage, stakeholder-summary, and tdd. The new long-form doc docs/skills/han-atlassian/investigate-to-confluence.md was added for the new skill below, and the /investigate write-up backing the /tdd change was filed at docs/plans/tdd-failure-characterization/investigation.md.

han-atlassian v2.1.0

New skill: investigate-to-confluence

A new skill investigate-to-confluence runs the core /investigate skill to root-cause a bug or unexpected behavior, writes the investigation report to a /tmp/ file (changing no code), shows it for review, then publishes that single report as one Confluence page to a user-specified location through /markdown-to-confluence. Added in han-atlassian/skills/investigate-to-confluence/SKILL.md, contributed by @mxriverlynn in #77.

Declared han-planning and han-coding dependencies

han-atlassian/.claude-plugin/plugin.json now declares han-planning and han-coding alongside han-core. The plugin's wrapper skills run skills from each, so all three are required dependencies; the manifest previously declared only han-core.

han-coding v2.1.0

/tdd writes regression tests for bug fixes

The /tdd skill now distinguishes net-new behavior from a fix to existing broken behavior, and for the fix case it drives the test toward what the code should do (red while the bug is present, green once the fix lands) rather than toward the error the bug currently raises. The change lands at four points in han-coding/skills/tdd/SKILL.md (the Step 1 scope report, the Step 2 test list, the Red-phase pre-run assertion-direction check, and the first-run-pass diagnostic) and is reinforced in three references: bdd-framing.md sharpens the Then clause and adds the anti-pattern of asserting the buggy behavior, failure-modes.md adds a named failure mode for asserting the bug instead of the fix, and tdd-loop.md points its observed-failure gate at the new diagnostic. The carve-out preserves legitimate assertRaises-style tests where raising is the specified desired behavior. Contributed by @mxriverlynn in #76.

han-planning v2.0.1

The /plan-a-phased-build skill description gained a cross-reference clarifying that it does not break a plan into independently-grabbable work items, pointing to /plan-work-items instead. Description text only, no behavior change.

Full changelog: https://github.com/testdouble/han/blob/v4.1.0/CHANGELOG.md#v410
Full Changelog: v4.0.0...v4.1.0

This release renames every plugin in the suite from a dotted name to a hyphenated name: han.core becomes han-core, han.coding becomes han-coding, han.planning becomes han-planning, han.github becomes han-github, han.reporting becomes han-reporting, han.feedback becomes han-feedback, han.atlassian becomes han-atlassian, and han.plugin-builder becomes han-plugin-builder. The parent meta-plugin han keeps its name and moves to 4.0.0; every renamed child goes major as well: han-core to 2.0.0, han-planning to 2.0.0, han-coding to 2.0.0, han-github to 2.0.0, han-reporting to 2.0.0, han-feedback to 2.0.0, han-atlassian to 2.0.0, and han-plugin-builder to 2.0.0. The rename is breaking because a plugin name is both its install identity and the namespace prefix for its agents (dispatching han.core:research-analyst is now han-core:research-analyst), so any saved install reference, dependency entry, or namespaced agent dispatch using the old dotted name breaks and must move to the hyphenated name. The rename was required for Codex marketplace support: a dot in a plugin name breaks Codex, where the name doubles as the skill and agent namespace prefix, so the whole suite needed Codex-safe (dot-free) names. This release also adds the new opt-in han-linear plugin at 1.0.0, carrying the work-items-to-linear skill.

What's Changed

• Plugin builder guidance - vendoring the skills with the guidance by @mxriverlynn in #71
• Add han.linear plugin: work-items-to-linear skill by @nafeger in #61
• Support Codex marketplace by @oppegard in #68
• Hyphenate names by @mxriverlynn in #72

han v4.0.0

Breaking: plugins renamed from dots to hyphens

Every plugin in the suite was renamed from its dotted name to a hyphenated name: han.core to han-core, han.coding to han-coding, han.planning to han-planning, han.github to han-github, han.reporting to han-reporting, han.feedback to han-feedback, han.atlassian to han-atlassian, and han.plugin-builder to han-plugin-builder. The parent han plugin keeps its name. A plugin name is its install identity and the namespace prefix for that plugin's agents, so a namespaced dispatch like han.core:research-analyst is now han-core:research-analyst. Any saved install reference, dependencies entry, or namespaced agent dispatch using an old dotted name must move to the hyphenated name. The rename was driven by Codex: a dot in a plugin name breaks Codex, where the name doubles as the skill and agent namespace prefix, so supporting the Codex marketplace required dot-free names across the suite. New guidance han-plugin-builder/skills/guidance/references/claude-marketplace-and-plugin-configuration/plugin-naming.md records the rule that a plugin name must be kebab-case with no dot.

Codex marketplace support

The suite gains a Codex marketplace manifest at .agents/plugins/marketplace.json in the repo root, and every plugin directory gains a .codex-plugin/plugin.json. This is the suite-level change that motivated the rename, since Codex cannot use a dotted plugin name. Contributed by @oppegard in #68, which added the Codex plugin scaffolding, switched the suite to Codex-safe plugin names, clarified the Codex install limits, and pointed the Codex metadata to Test Double.

Documentation

The documentation sweep under docs/ moved the long-form skill and agent docs from dotted paths to hyphenated paths: docs/skills/han.core/... became docs/skills/han-core/... and the agent docs moved the same way. Broken cross-skill links were fixed, docs/skills/han-linear/work-items-to-linear.md was added, and CLAUDE.md, README.md, CONTRIBUTING.md, docs/semantic-versioning.md, docs/choosing-a-han-plugin.md, and the skills and agents indexes were updated to the hyphenated names. CLAUDE.md notes plugin-naming.md in its config-guidance map, and han-linear was wired into the top-level docs.

han-core v2.0.0

Renamed from han.core to han-core, a breaking change to its install identity and to the namespace prefix for its agents (han.core:research-analyst is now han-core:research-analyst). Its Codex .codex-plugin/plugin.json packaging was added. The skill and agent file contents did not otherwise change; their files moved with the rename.

han-planning v2.0.0

Renamed from han.planning to han-planning, a breaking change to its install identity and agent namespace prefix. Its Codex .codex-plugin/plugin.json packaging was added. The skill file contents did not otherwise change; their files moved with the rename.

han-coding v2.0.0

Renamed from han.coding to han-coding, a breaking change to its install identity and agent namespace prefix. Its Codex .codex-plugin/plugin.json packaging was added. The skill file contents did not otherwise change; their files moved with the rename.

han-github v2.0.0

Renamed from han.github to han-github, a breaking change to its install identity and agent namespace prefix. Its Codex .codex-plugin/plugin.json packaging was added. The skill file contents did not otherwise change; their files moved with the rename.

han-reporting v2.0.0

Renamed from han.reporting to han-reporting, a breaking change to its install identity and agent namespace prefix. Its Codex .codex-plugin/plugin.json packaging was added. The skill file contents did not otherwise change; their files moved with the rename.

han-feedback v2.0.0

Renamed from han.feedback to han-feedback, a breaking change to its install identity and agent namespace prefix. Its Codex .codex-plugin/plugin.json packaging was added. The skill file contents did not otherwise change; their files moved with the rename.

han-atlassian v2.0.0

Renamed from han.atlassian to han-atlassian, a breaking change to its install identity and agent namespace prefix. Its Codex .codex-plugin/plugin.json packaging was added. The skill file contents did not otherwise change; their files moved with the rename.

han-plugin-builder v2.0.0

Renamed from han.plugin-builder to han-plugin-builder, a breaking change to its install identity and agent namespace prefix. Its Codex .codex-plugin/plugin.json packaging was added. The guidance skill also gained the vendoring work from #71 by @mxriverlynn, so /guidance init vendors the plugin-building skills alongside the guidance. The skill file contents did not otherwise change beyond that work; their files moved with the rename.

han-linear v1.0.0 (new)

A new opt-in plugin carrying the work-items-to-linear skill, contributed by @nafeger in #61. The skill creates one Linear issue per slice from a /plan-work-items work-items file, resolving the target team's real states, labels, Projects, and members through the Linear MCP server and linking within-file dependencies as native Linear "blocked by" relations. The --assignee flag resolves through get_user so the me token works (WARN-001). han-linear depends on han-core, requires a configured Linear MCP server, and is not bundled by the han meta-plugin, so it is installed on its own.

Full changelog: https://github.com/testdouble/han/blob/v4.0.0/CHANGELOG.md#v400
Full Changelog: v3.4.1...v4.0.0

This release vendors the plugin-building skills, not the guidance alone, when /guidance init runs in a repository, and documents the result. The parent han plugin moves to 3.4.1 and han.plugin-builder moves to 1.2.1. No other plugins change.

What's Changed

• Direct commits since v3.4.0; see the full changelog below.

han v3.4.1

The suite-level work is documentation. Two new how-to guides were added: docs/how-to/create-a-new-skill.md is the end-to-end recipe for authoring a skill with /skill-builder, and docs/how-to/create-a-new-agent.md is the same for an agent with /agent-builder. docs/how-to/README.md was updated to index both. The long-form doc docs/skills/han.plugin-builder/guidance.md was updated to describe the new three-skill vendoring behavior of init and update, and docs/skills/han.plugin-builder/skill-builder.md and docs/skills/han.plugin-builder/agent-builder.md had minor updates. README.md was reorganized, and CLAUDE.md, docs/choosing-a-han-plugin.md, docs/skills/README.md, and docs/how-to/build-a-plugin-that-depends-on-han.md were updated to reflect the renamed vendored skills (plugin-guidance, plugin-skill-builder, plugin-agent-builder) and the three-skill vendoring. Em-dashes that had been introduced in the guidance-vendoring docs were removed.

han.plugin-builder v1.2.1

The /guidance skill's init and update modes previously vendored only the guidance documents into .claude/plugin-building-guidance/ plus a path-scoped rule index. They now vendor three skills into .claude/skills/ under a plugin- prefix so they never collide with this plugin's own slash commands: a guidance-only plugin-guidance skill whose references/ directory holds the single in-repo copy of the guidance documents, plus plugin-skill-builder and plugin-agent-builder, with their names, cross-references, and guidance paths rewritten to the vendored copy. update mode now refreshes every vendored skill in full and regenerates the rule index, confirming the skills are installed first. A new asset han.plugin-builder/skills/guidance/assets/guidance-portable-SKILL.md holds the portable SKILL.md template used when vendoring the guidance-only skill. han.plugin-builder/skills/guidance/assets/rule-index-body.md and han.plugin-builder/skills/guidance/scripts/init-guidance.sh were updated to perform this vendoring, and the guidance skill's SKILL.md description and its Initialization and Update mode text were rewritten to match.

Full changelog: https://github.com/testdouble/han/blob/v3.4.1/CHANGELOG.md#v341
Full Changelog: v3.4.0...v3.4.1

This release adds two interview-driven builder skills to the opt-in han.plugin-builder plugin: /skill-builder and /agent-builder. Each one walks a new skill's or agent's design tree decision-by-decision through an evidence-based interview, then reviews the finished files against the plugin-building guidance and applies every fix it finds. The guidance skill gains an update mode for refreshing an already-vendored copy. The parent han plugin moves to 3.4.0 and han.plugin-builder moves to 1.2.0. No other plugins change.

What's Changed

• Update /investigate output ordering by @mxriverlynn in #69
• Plugin builder skills: skill and agent builders by @mxriverlynn in #70

han v3.4.0

The suite-level work is documentation for the two new builder skills. Long-form operator docs were added at docs/skills/han.plugin-builder/skill-builder.md and docs/skills/han.plugin-builder/agent-builder.md, and docs/skills/han.plugin-builder/guidance.md was updated for the new update mode. The skills index docs/skills/README.md, the project map CLAUDE.md, README.md, and docs/concepts.md were updated to list and describe the new builders without a hardcoded count.

The long-form doc docs/skills/han.github/post-code-review-to-pr.md was corrected to state that the optional fix plan lists findings ordered by priority, Critical first, matching han.github/skills/post-code-review-to-pr/SKILL.md.

han.plugin-builder v1.2.0

Two new skills join the plugin from @mxriverlynn in #70. /skill-builder builds a new Claude Code skill from scratch through a relentless, evidence-based interview that walks the skill's design tree (entity fit, use cases, name, description, workflow steps, tools, progressive-disclosure layout), then reviews the finished SKILL.md and any references/, scripts/, or assets/ against the plugin-building guidance and applies every fix. /agent-builder does the same for a new agent, walking entity fit, domain focus and vocabulary, role identity, anti-patterns, description, model tier, tools, and self-containment, and reviewing the finished self-contained agent file against the guidance. Both explore the target plugin before asking, recommend an answer with its rationale for every question, and never batch questions.

The guidance skill gained an update mode that refreshes an already-vendored guidance copy and its rule index, alongside the existing serve and init modes. han.plugin-builder/skills/guidance/scripts/init-guidance.sh was adjusted to support it.

Full changelog: https://github.com/testdouble/han/blob/v3.4.0/CHANGELOG.md#v340
Full Changelog: v3.3.1...v3.4.0

This release refines the /investigate skill's output report and the operator doc that describes it. The parent han plugin moves to 3.3.1, and han.coding moves to 1.0.1. No other plugins change. The work is entirely a restructuring of the investigation report for readability: the report leads with its conclusion, omits sections that have no content, and renames "Final Summary" to "Summary".

What's Changed

• Direct commits since v3.3.0; see the full changelog below.

han v3.3.1

The long-form operator doc docs/skills/han.coding/investigate.md was updated to match the reworked /investigate output. It now describes the report as conclusion-first (BLUF), documents that sections appear only when they have meaningful content, and reflects the "Summary" rename along with the new section order (Problem Statement, Root Cause Analysis, Planned Fix, followed by supporting detail).

han.coding v1.0.1

The /investigate output template in han.coding/skills/investigate/references/template.md was restructured for readability. The summary moved to the top of the report and was renamed from "Final Summary" to "Summary", the narrative now runs Problem Statement, Root Cause Analysis, Planned Fix, and the supporting detail below it (Evidence Summary, Validation Results, conditional Coding Standards Reference) is ordered by dependency. A three-way "Summary" heading collision was resolved by renaming the nested subsections to "Root Cause" and "Approach", and the Summary now carries a reader key pointing to where (E#) and (V#) items are defined.

Output sections are now lazy-created: the report includes a section only when it has meaningful content, and empty sections are omitted rather than emitting placeholder or "N/A" headings. This is stated at the top of han.coding/skills/investigate/references/template.md and enforced in han.coding/skills/investigate/SKILL.md, which also notes that fill order is workflow order, not the template's on-page order.

Full changelog: https://github.com/testdouble/han/blob/v3.3.1/CHANGELOG.md#v331
Full Changelog: v3.3.0...v3.3.1

This release reorganizes the Han suite: han.core was split, with code-writing skills moving to the new han.coding (which also adds a new refactor skill) and the planning skills moving to the new han.planning. Both new plugins depend on han.core and are bundled by the han meta-plugin, so no bundled-suite installer loses anything. The parent han plugin moves to 3.3.0. han.core moves to 1.2.0 (eleven skills removed, the specialist agents stay). Two new plugins join the suite at 1.0.0: han.planning and han.coding. han.github moves to 1.2.0, han.atlassian to 1.1.0, and han.plugin-builder to 1.1.0. han.reporting moves to 1.0.1 and han.feedback to 1.1.1.

What's Changed

• work-items-to-issues: PR fallback and feature-scoped assets by @afrerich in #53
• Issue #51 - Reducing Context Footprint by @mxriverlynn in #58
• Clarify skill invocation model in concepts.md (#54) by @mxriverlynn in #59
• issue 57: code review output size by @mxriverlynn in #60
• Han.atlassian: plan a feature in confluence by @mxriverlynn in #62
• Add han.coding and move tdd skill into it by @mxriverlynn in #63
• Nest skill and agent docs into per-plugin folders by @mxriverlynn in #64
• Add refactor skill to han.coding by @mxriverlynn in #65
• Moving skills into han.coding by @mxriverlynn in #66
• Plugin organizing: han.planning by @mxriverlynn in #67

Issues closed

• Reduce always-loaded context footprint of Han agent and skill descriptions (#51) — opened by @mxriverlynn, fixed in #58 by @mxriverlynn
• Add a refactor skill (#52) — opened by @mxriverlynn, fixed in #65 by @mxriverlynn
• docs: concepts.md implies skills are slash-command-only, but no skill sets disable-model-invocation (all are model-invocable) (#54) — opened by @chipit24, fixed in #59 by @mxriverlynn
• Reduce the size of the code-review skill's output without losing meaningful information or specified behavior (#57) — opened by @mxriverlynn, fixed in #60 by @mxriverlynn

han.planning v1.0.0 (new)

A new bundled child plugin from @mxriverlynn in #67 that depends on han.core and is installed by the han meta-plugin. It holds the five planning skills moved out of han.core: /plan-a-feature, /plan-implementation, /plan-a-phased-build, /plan-work-items, and /iterative-plan-review. It vendors references/evidence-rule.md and references/yagni-rule.md for those skills.

han.coding v1.0.0 (new)

A new bundled child plugin from @mxriverlynn that depends on han.core and is installed by the han meta-plugin. It ships seven skills. Six moved out of han.core: /tdd (#63), then /code-review, /test-planning, /investigate, /coding-standard, and /architectural-analysis (#66). One is brand new: /refactor (#65), which restructures existing code without changing its behavior through a test-gated loop (a named target, a green suite over that target before any edit, a planned sequence of small named refactorings, the full suite re-run after each step, and hard stop rules on scope spread); its revert mechanic is git-optional and it ships its own context-detection script, with the backing research at docs/research/refactor-skill-research.md, closing issue #52. The /code-review skill carries a leaner output document from #60: it defers YAGNI procedure detail to the checklist, collapses a repeated dispatcher-tailoring disclaimer, dedupes a size-demotion rule, and compresses verification items that re-quote canonical rules, closing issue #57. The plugin vendors references/evidence-rule.md and references/yagni-rule.md.

han v3.3.0

The headline is the plugin reorganization: han.coding and han.planning join the suite as bundled child plugins, the han meta-plugin now depends on han.core, han.planning, han.coding, han.github, and han.reporting, and .claude-plugin/marketplace.json carries the new plugin entries and version bumps.

Documentation

In #64 the long-form docs under docs/skills/ and docs/agents/ were reorganized into per-plugin subfolders (docs/skills/han.core/, docs/skills/han.coding/, docs/agents/han.core/, and the rest), the README plugin list was converted to a table and simplified, and a full doc sweep fixed dispatcher accuracy and filled invocation gaps. In #59 docs/concepts.md was corrected to state that skills are model-invocable and not slash-command-only (no Han skill sets disable-model-invocation), closing issue #54 opened by @chipit24. The context-footprint investigation was recorded under docs/plans/reduce-context-footprint/.

Repository maintenance

The .claude/ repo-maintenance tooling was updated so han-update-documentation discovers skill roots dynamically.

han.core v1.2.0

Eleven skills were removed from han.core and now live in the two new plugins: the five planning skills moved to han.planning and the six code-writing skills moved to han.coding. What remains in han.core is /issue-triage, /research, /architectural-decision-record, /gap-analysis, /project-discovery, /project-documentation, /runbook, plus all the specialist agents. The plugin description was updated to point planning skills at han.planning. In #58 the heaviest agent descriptions (data-engineer, devops-engineer, information-architect, junior-developer, on-call-engineer, project-manager, system-architect, user-experience-designer) and several skill descriptions were trimmed of methodology name-drops to cut always-loaded context, closing issue #51.

han.github v1.2.0

In #53 from @afrerich, the /work-items-to-issues screenshot upload (scripts/upload-screenshots.sh) gained a protected-branch fallback: when a direct write to the default branch is rejected with HTTP 409, it commits the PNGs to an assets branch, opens a pull request, and prints the PR URL, while the embedded image URLs always name the default branch so inline designs render once that assets PR merges. Assets are now namespaced by a <feature-slug> segment (the kebab-cased plan-folder basename) so two features publishing to the same repo do not collide. PUT failures are now propagated and add/update is gated on GET status. The change touched references/issue-template.md, reference-artifact-inventory.md, screenshot-embed-rules.md, work-items-file-format.md, and the work-items-to-issues SKILL.md.

han.atlassian v1.1.0

A new skill, plan-a-feature-to-confluence, from @mxriverlynn in #62: it runs /plan-a-feature and then publishes the spec as a parent Confluence page with each companion artifact (decision log, team findings, technical notes) as a child page, in a single create pass. Its sibling skills markdown-to-confluence, project-documentation-to-confluence, and work-items-to-jira each got minor edits to add bidirectional cross-references.

han.plugin-builder v1.1.0

A new reference file, agent-building-guidelines/agent-description-length.md, captures the agent description-length budget from issue #51 (#58). skill-building-guidance/skill-composition.md was rebuilt around orchestration versus data-fetch, with edits to troubleshooting.md, agent-domain-focus.md, agent-model-selection.md, iterative-plugin-development.md, optional-git-repositories.md, specialization-and-model-selection.md, the guidance SKILL.md, and rule-index-body.md.

han.reporting v1.0.1

Doc-sweep wording edits to html-summary/SKILL.md and stakeholder-summary/SKILL.md: minor description and context changes only, no behavior change.

han.feedback v1.1.1

A doc-sweep description trim to han-feedback/SKILL.md, no behavior change.

Full changelog: https://github.com/testdouble/han/blob/v3.3.0/CHANGELOG.md#v330
Full Changelog: v3.2.0...v3.3.0