Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/vasilyu1983/AI-Agents-publicnpx agentmods add skills/vasilyu1983/ai-agents-public/research-gitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/vasilyu1983/ai-agents-public/research-git)<a href="https://agentmods.dev/skills/vasilyu1983/ai-agents-public/research-git"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/research-git/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/vasilyu1983/ai-agents-public/research-git"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/research-git.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00039 | $0.07065 |
| Opus 5.5 | $0.00016 | $0.02826 |
| Sonnet 5.5 | $0.00008 | $0.01413 |
| Haiku 4.5 | $0.00004 | $0.00707 |
Grade A, and why
research-git scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 19d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 390 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo Research
Scan public GitHub repos for agent skills (SKILL.md ecosystem), dev practices (git/PR/CI workflows from real teams), or code patterns (framework idioms, config layouts) — then merge validated insights into the local catalog with full attribution.
Manual extraction is unsustainable. The agent-skill ecosystem is large and still growing (see data/sources.json for named registries and their scale), before counting the repos worth scanning for their CI, testing, or i18n setups. This skill makes the scan repeatable and the merge auditable.
Navigation
- Quick Reference — entry-point table by need
- Four Modes — skill / practice / code / killer-feature targeting
- When to Use and When NOT to Use
- Default Workflow — discover → triage → fetch → diff → merge
- Output Contract — per-mode scan report shape
- Promotion Check — five checks before a finding is promoted
- references/discovery-protocol.md — discovery commands and triage (includes velocity/dependency signals and beyond-GitHub hosts)
- references/code-pattern-mining.md — Mode C extraction
- references/attribution-rules.md — licensing
- references/code-search-syntax.md — code-search qualifiers the API accepts (legacy engine, not the web UI),
gh search codeCLI, rate-limit strategy, example queries per mode - references/graphql-triage.md — single-repo health query, batch-alias pattern, repo discovery via
searchconnection - references/signal-quality.md — fake-star/astroturf detection: fork ratio, GH Archive spike queries, contributor account-age checks
- references/git-history-forensics.md — single-repo git-history verification: pickaxe
-S/-G,blame -w -C -M,bisect run,range-diff, whengit loglies - data/sources.json — registries, authors, hot lists, ecosystem analytics, cross-host registries
What ships with it
22 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 363 B
- data/sources.json 18 KB
- learnings.consolidated.md 588 B
- learnings.md 839 B
- references/apply-protocol.md 5.0 KB
- references/attribution-rules.md 6.7 KB
- references/claude-code-ecosystem-catalog.md 10 KB
- references/code-pattern-mining.md 6.9 KB
- references/code-search-syntax.md 8.2 KB
- references/discovery-protocol.md 10 KB
- references/extraction-protocol.md 4.7 KB
- references/git-history-forensics.md 12 KB
- references/graphql-triage.md 9.1 KB
- references/insight-mining.md 4.5 KB
- references/killer-feature-mining.md 12 KB
- references/practice-scan-targets.md 7.0 KB
- references/signal-quality.md 8.2 KB
- scripts/diff_against_local.sh 4.5 KB runs code
- scripts/fetch_repo_assets.sh 15 KB runs code
- scripts/search_repos.sh 10 KB runs code
- scripts/test_fetch_manifest.py 2.1 KB runs code
- scripts/test_research_git_scripts.py 13 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 19d ago Changed · +16 lines · +3 tokens per session 1598802eb63a
- 1mo ago Changed · +12 lines ab3e7001c552
- 1mo ago First seen · 362 lines · 36 tokens per session scan A 3433740108d4
research-git is a skill published in the GitHub repository vasilyu1983/AI-Agents-public (101 stars, last pushed 9d ago), licensed MIT. It adds 39 tokens to every session and 7,065 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
git-advanced-workflows
Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
what-did-i-get-done
Summarize authored commits over a user-specified time period into a concise update.
block-no-verify-hook
Configure a PreToolUse hook to prevent AI agents from skipping git pre-commit hooks with --no-verify and other bypass flags. Use when setting up Claude Code projects that enforce commit quality gates.
cross-repo-cache
Check if cross-repo coordinator results can be reused, avoiding redundant Sonnet agent launches. Compares peer repo git hashes against stored hashes from last coordinator run. Triggers on: entering Phase 1.4.1, checking cross-repo cache, before discovering peers. Returns CROSSREPOCACHEHIT with cached status or…
atlas-changelog
Maintain per-repo and cross-repo changelogs — append structured entries after agent work. Use when asked to "log this change", "update changelog", "what changed", "change history".