Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add fmind/dot --skill repository-historygit clone --depth 1 https://github.com/fmind/dotWrote 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/fmind/dot/repository-history)<a href="https://agentmods.dev/skills/fmind/dot/repository-history"><img src="https://agentmods.dev/badge/skills/fmind/dot/repository-history/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/fmind/dot/repository-history"><img src="https://agentmods.dev/badge/skills/fmind/dot/repository-history.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00022 | $0.00715 |
| Opus 5.5 | $0.00009 | $0.00286 |
| Sonnet 5.5 | $0.00004 | $0.00143 |
| Haiku 4.5 | $0.00002 | $0.00072 |
Grade A, and why
repository-history 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 12d 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository History
Explain why tracked code exists from Git lineage and recorded rationale. Keep present-day debugging in systematic-debugging and external API choices in research-brief.
Workflow
- Bound the question: path, symbol, revision range, and the decision the history should inform; keep it small enough that every cited commit can be inspected.
- Trace evidence: follow investigation.md for coverage, blame, line history, pickaxe, renames, commit inspection, and exact PR mapping through gh.
- Report: the investigation's history note, rating confidence with the scale in Gotchas.
Gotchas
- Investigation is read-only: Preserve the working tree and existing refs. Fetch missing objects into an isolated clone when needed for the requested investigation; use a disposable worktree for bisect experiments. Pulling into the working tree, rewriting history, and contacting authors require authority for those effects.
- Current blame is not original authorship: a committer is not necessarily the designer, and a message can state intent without proving the constraint still holds; redact email addresses from returned evidence.
- Rate confidence by evidence:
Highneeds explicit rationale that agrees with the patch, tests, and later history;Mediumhas agreeing lineage and co-change without stated rationale;Lowrests on blame, one title match, a semantic search, sparse history, or an ancestry break; otherwise sayUNKNOWN. - Downgrade stale rationale: A revert describes a past decision; downgrade it when later architectural changes contradict the trade-off.
- Missing history is not absence: Never infer that a missing commit or discussion does not exist; state the gap and lower confidence.
Documentation
- git blame · git log · Pull requests associated with a commit
- Adapted from awesome-llm-apps commit-archaeologist.
- Companion skills: systematic-debugging (reproduce a current failure), repository-review (one change or cross-cutting audit), research-brief (current external facts), github-issues (remote issue state).
What ships with it
1 file 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.
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.
- 12d ago Changed · -1 lines a3e96d241a72
- 14d ago Changed f33acd4759ad
- 15d ago Changed · -1 lines · -1 tokens per session 2df699b0cc0e
- 23d ago Changed 9b454ad09bfd
- 29d ago Changed da6005560ae9
- 1mo ago Changed · +1 lines · -14 tokens per session 44a7c0876a0c
- 1mo ago Changed ee40fab1cfab
- 1mo ago Changed · -37 lines · -11 tokens per session 893784bf299f
- 1mo ago First seen · 74 lines · 48 tokens per session scan A 790211b19bb5
repository-history is a skill published in the GitHub repository fmind/dot (12 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 715 once invoked, about $0.0001 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
release
Cut or verify a versioned release — bump semver, generate the changelog with git-cliff, tag and publish on GitHub, or reconcile an already-published tag and assets.
github-repository
Configure a GitHub repository's metadata (description, homepage, topics) and solo-developer settings via gh, derived from the codebase. Use when setting up or tidying a repo's GitHub settings.
lefthook
Canonical lefthook git-hooks setup — pre-commit (format, check, secret scan) and pre-push (test), each delegating to mise run tasks. Use when configuring or debugging git hooks.
git-add-commit-push
Stage, commit (Conventional Commits), and push in one flow, auto-healing lefthook pre-commit and pre-push failures. Use when committing and pushing work end-to-end.
github-issues
Manage GitHub issues with gh: confirm repo and state, deduplicate, preserve evidence, and verify authorized creation, edits, labels, comments, or closure.
github-pull-request
Create or update a GitHub pull request with a structured What / Why / How / Test-plan body. Use when opening or updating a PR for the current branch.