intent-layer

Plugin intent-layer from marketplace orban in orban/claude-skills. Commands read from the repo's manifest — 1 month ago.

Skills (11)

• clean

  Remove the Intent Layer from a repository. Deletes all child AGENTS.md files and removes the Intent Layer section from the root CLAUDE.md.

• intent-layer-compound

  End-of-cycle learning capture and triage. Run after completing a feature, fixing a bug, or finishing any significant work. Reviews pending learnings, analyzes conversation for undocumented insights, and integrates into the Intent Layer with appropriate scope (global workflow vs local code).

• intent-layer-health

  Quick health check for Intent Layer - validates nodes, checks staleness, reports coverage gaps

• intent-layer-maintenance

  Use when maintaining an existing Intent Layer, during quarterly reviews, after significant code changes, when something confused you, or when user asks to audit/update CLAUDE.md or AGENTS.md files.

• intent-layer-onboarding

  Get oriented in an unfamiliar codebase using its Intent Layer. Use when joining a new project, exploring a codebase for the first time, or helping someone understand "where do I start?" questions.

• intent-layer-query

  Query the Intent Layer to answer questions about the codebase. Use when asking "what owns X?", "where should I put Y?", "what constraints apply to Z?", or navigating an unfamiliar codebase using its AGENTS.md hierarchy.

• intent-layer

  Set up hierarchical Intent Layer (AGENTS.md files) for codebases. Use when initializing a new project, adding context infrastructure to an existing repo, user asks to set up AGENTS.md, add intent layer, make agents understand the codebase, or scaffolding AI-friendly project documentation.

• git-history

  Extract Intent Layer content from git history. Analyzes commits, PRs, and blame to discover pitfalls, contracts, architecture decisions, and entry points that should be documented in AGENTS.md files.

• pr-review-mining

  Extract Intent Layer content from GitHub PR descriptions and review comments. Mines merged PRs for pitfalls, contracts, architecture decisions, and anti-patterns that should be documented in AGENTS.md files.

• pr-review

  Review PRs against the Intent Layer. Use for reviewing AI-generated PRs or having AI review human PRs. Provides risk scoring, checklists, and contract verification.

• review-mistakes

  Interactive review of pending mistake reports from the learning loop. Walk through each report with the user, accepting/rejecting/discarding as appropriate.

Subagents (5)

• AGENTS
• auditor

  Find drift between Intent Layer nodes and current code state. Use for quarterly maintenance, post-merge review, or when hook flags accumulate. - Run validator across all nodes in parallel - Compare node timestamps vs code change timestamps - Identify stale sections where code changed but node didn't

• change-tracker

  Identifies Intent Layer nodes affected by code changes for targeted validation

• explorer

  Analyze a directory and propose AGENTS.md content. Use when setting up new Intent Layer nodes or when a directory is flagged as needing coverage. - Analyze directory structure and semantic boundaries - Extract contracts, patterns, and entry points from code - Mine git history for pitfalls and anti-p

• validator

  Deep validation that an Intent Layer node accurately reflects its codebase. Use after creating/updating nodes or as part of PR review. - Compare documented contracts against actual code enforcement - Verify entry points exist and are accurate - Check documented patterns are actually followed - Flag

Hooks (5)

• PostToolUse

  ${CLAUDE_PLUGIN_ROOT}/scripts/post-edit-check.sh "$TOOL_INPUT"

• PostToolUseFailure

  ${CLAUDE_PLUGIN_ROOT}/scripts/capture-tool-failure.sh

• SessionStart

  ${CLAUDE_PLUGIN_ROOT}/scripts/inject-learnings.sh

• PreToolUse

  ${CLAUDE_PLUGIN_ROOT}/scripts/pre-edit-check.sh

• Stop

  ${CLAUDE_PLUGIN_ROOT}/scripts/stop-learning-check.sh

Similar plugins