code review by agent-sh
Repo Intel Skill agent-sh/repo-intel
Use when user asks to "run repo intel", "generate repo map", "analyze repo", "query hotspots", "check ownership", or "bus factor". Unified static analysis - git history, AST symbols, project metadata.
What it changes View full report → Passed 16 of 19 test cases with the skill, and 7 of 19 without it.
Without skill 36%
With skill 82%
Checks it passed that the model alone missed and 9 more in the full report
10 fixed8 passed either way4 still failing0 broke
Pass-rate lift +45 pp
Tokens -42%
Agent turns 0%
Response time -66% Model gemini-3.6-flashMeasured 8/14/2026 v1 18 of 22 cases passed with skill · 19 comparable
Use this skill Claude Code DecimalAI agent CLI & files
Save it into your project's skills folder. Claude Code picks it up in its next session.
curl -fsSL --create-dirs -o .claude/skills/agent-sh-repo-intel/SKILL.md https://app.decimal.ai/s/agent-sh-repo-intel/SKILL.md Copy command Copy SKILL.md
Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add agent-sh-repo-intel, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"
Linked stays up to date: your agents get the author's new versions automatically.
Editable copy is yours to change; the author's updates won't reach it.
Install linked skill Create editable copy
1 · One-time — install the CLI (
docs ↗ )
$ pip install "decimalai>=0.15"Copy
2 · Get the skill — writes .agents/skills/agent-sh-repo-intel/ and pins it in .decimal/skills.lock
$ decimalai skills add agent-sh-repo-intelCopy
Copy link Copy README badge Copy SKILL.md No CLI? Get the same file — curl · raw file $ curl -fsSL --create-dirs -o .claude/skills/agent-sh-repo-intel/SKILL.md https://app.decimal.ai/s/agent-sh-repo-intel/SKILL.mdCopy
Safety checks: 3 of 3 passed
Code scan Clean Intent Passed Content Clean
Overview Benchmark Contents Activity Versions 1 Ratings 0
See it in action One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
Prompt What subcommand string should be issued to run a non-destructive incremental refresh of analysis metadata?
What was checked, without and with the skill Checked Without skill With skill /repo-intel update Triggers incremental sync without rebuilding entire history
Show both answers
What's inside The instructions your model reads when the skill loads.
SKILL.md 57 lines single file
Repo Intel Skill
Unified static analysis - git history intelligence, AST symbol mapping, and project metadata via agent-analyzer.
Parse Arguments
const args = '$ARGUMENTS'.split(' ').filter(Boolean);
const action = args.find(a => !a.startsWith('--')) || 'status';
const force = args.includes('--force');
Primary Responsibilities
Initialize on demand (/repo-intel init)Update incrementally (/repo-intel update)Query git history data (/repo-intel query hotspots)Check status and staleness (/repo-intel status)Validate output with the map-validator agent
Core Data Contract
Repo intel data is stored in the platform state directory:
Claude Code: .claude/repo-intel.json, .claude/repo-map.json
OpenCode: .opencode/repo-intel.json, .opencode/repo-map.json
Codex CLI: .codex/repo-intel.json, .codex/repo-map.json
Behavior Rules
Never install dependencies without explicit user consentAlways validate output with map-validator after init/updatePrefer incremental update unless data is stale or history rewritten
When to Suggest Repo Intel
If a user asks for drift detection, documentation alignment, or repo analysis and repo-intel data is missing:
Repo intel data not found. For better analysis, run:
Track record Benchmark 16 / 19
test cases passed, vs 7 / 19 without
Adoption
Users 0
Times used 0 View activity → Safety and source details
SkillSafety ✓ 3 of 3 passed ✓ Code scan 15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026
View 15 scanner checks live_secret remote_code_execution reverse_shell data_exfiltration ssrf_metadata agent_snooping anti_refusal destructive_commands obfuscated_unicode unicode_homoglyph opaque_blob suspicious_url tool_overreach trigger_abuse prompt_injection_phrasing
✓ Intent Safe
LLM judge · does the skill do what it claims
✓ Content Clean
LLM judge · policy & harmful-content review
Source Imported License MITImported 8/3/2026Version v1