Codebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code detection, and architectural decisions via MCP.
Python aicode-complexitycode-healthcode-intelligencecode-qualitydead-codedeveloper-toolsdocumentationgit-analyticsmcpopen-sourcepythonrefactoringstatic-analysistechnical-debt
fix(plugins): carry the Fix first wording into the shared code-health skill source (#2836)
Raghav Chamadiyad5d9042c3b06
diff --git a/plugins/codex/skills/code-health/SKILL.md b/plugins/codex/skills/code-health/SKILL.mdindex eabe11796..b5e97b224 100644--- a/plugins/codex/skills/code-health/SKILL.md+++ b/plugins/codex/skills/code-health/SKILL.md@@ -14,8 +14,8 @@ not just *bigger*.## Pick the mode by what you pass-- **Dashboard** — `get_health()` (no targets): a `directive` naming what to fix- first, then repo-level KPIs and the lowest-scoring files. Start here for "how+- **Dashboard**: `get_health()` (no targets): `fix_first`, the ranked list of+ what to fix first, then repo-level KPIs and the lowest-scoring files. Start here for "howhealthy is this codebase?" or "what should we clean up?".- **Targeted** — `get_health(targets=["src/x.py", "src/y.py"])`: per-file scoreand the specific marker findings driving it. Use before/after a refactor,@@ -33,9 +33,9 @@ not just *bigger*.## How to use the results-1. For "what should I refactor?" → dashboard mode, lead with `directive`, then- `get_health(targets=[worst files], include=["refactoring"])` and present the- ranked plans, not just the scores.+1. For "what should I refactor?" → dashboard mode, lead with `fix_first`; open+ an item with `get_health(fix_id=...)` for its steps and the tests to run,+ and present the plan, not just the scores.2. Rank by `weighted_deficit`, not `score` — the score floors at 1.0.3. For a specific file → report the score, the top 2–3 marker findings, andwhat each one means in plain language. Avoid dumping the raw payload.diff --git a/plugins/shared/skills/code-health.md b/plugins/shared/skills/code-health.mdindex 1c9690abf..eb3d61f27 100644--- a/plugins/shared/skills/code-health.md+++ b/plugins/shared/skills/code-health.md@@ -27,8 +27,8 @@ not just *bigger*.## Pick the mode by what you pass-- **Dashboard** — `get_health()` (no targets): a `directive` naming what to fix- first, then repo-level KPIs and the lowest-scoring files. Start here for "how+- **Dashboard**: `get_health()` (no targets): `fix_first`, the ranked list of+ what to fix first, then repo-level KPIs and the lowest-scoring files. Start here for "howhealthy is this codebase?" or "what should we clean up?".- **Targeted** — `get_health(targets=["src/x.py", "src/y.py"])`: per-file scoreand the specific marker findings driving it. Use before/after a refactor,@@ -46,9 +46,9 @@ not just *bigger*.## How to use the results-1. For "what should I refactor?" → dashboard mode, lead with `directive`, then- `get_health(targets=[worst files], include=["refactoring"])` and present the- ranked plans, not just the scores.+1. For "what should I refactor?" → dashboard mode, lead with `fix_first`; open+ an item with `get_health(fix_id=...)` for its steps and the tests to run,+ and present the plan, not just the scores.2. Rank by `weighted_deficit`, not `score` — the score floors at 1.0.3. For a specific file → report the score, the top 2–3 marker findings, andwhat each one means in plain language. Avoid dumping the raw payload.