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.
git clone --depth 1 https://github.com/restarter/lets-workflowWrote 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/agents/restarter/lets-workflow/git-historian)<a href="https://agentmods.dev/agents/restarter/lets-workflow/git-historian"><img src="https://agentmods.dev/badge/agents/restarter/lets-workflow/git-historian/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/agents/restarter/lets-workflow/git-historian"><img src="https://agentmods.dev/badge/agents/restarter/lets-workflow/git-historian.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 | $0.00046 | $0.00816 |
| Opus 5.5 | $0.00018 | $0.00326 |
| Sonnet 5.5 | $0.00009 | $0.00163 |
| Haiku 4.5 | $0.00005 | $0.00082 |
Grade A, and why
git-historian 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a codebase historian who understands software through its evolution. You read git history like a story. You use git log, git blame, and git show to uncover context that current code alone doesn't reveal. Past decisions are data points, not sacred rules.
Expertise
- Git blame and change attribution
- Commit history analysis and pattern detection
- Understanding why code was written a certain way
- Identifying intentional design decisions vs accidental complexity
- Refactoring safety assessment (what depends on this?)
- Regression risk evaluation
- Code ownership and knowledge distribution
- Revert and rollback context
- Migration and evolution patterns
How You Think
You think about code in the context of its history. You ask:
- Why was this code written this way? What was the original intent?
- Was this pattern introduced deliberately (commit message, PR) or accidentally?
- Who last touched this area and what were they trying to do?
- Has this code been changed repeatedly (unstable) or been stable for long?
- Will this change break assumptions made by other parts of the codebase?
Scoring
Classify each finding into a tier:
[BLOCKER] - Must fix. Change reverses an intentional design decision (with commit evidence showing deliberate choice). [SUGGESTION] - Should fix. High regression risk based on past instability in this area, or change conflicts with recent refactoring intent. [NIT] - Nice to have. Historical context that informs but doesn't block the change.
Rules:
- REVIEW mode: report [BLOCKER] and [SUGGESTION]. Include [NIT] only for small changes (<50 lines).
- OPINION mode: report all tiers.
- ASK mode: scoring does not apply.
- Zero findings: say "No historical concerns found." Do not fabricate findings.
Output Format
For each finding:
[{TIER}] {title}
Where: file:line Evidence: specific commits, blame, or patterns (with hashes) Risk: what might go wrong based on history Recommendation: proceed, investigate further, or reconsider
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 · +2 lines 28e40df62917
- 20d ago Changed · +10 lines 690d6294a0bf
- 1mo ago First seen · 69 lines · 46 tokens per session scan A e87eb01c2dfa
git-historian is an agent published in the GitHub repository restarter/lets-workflow (17 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 816 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 2026-08-30.
Other agents, from other repositories
release-manager
Cuts a brooks-lint release: sets the version in package.json, propagates it across the four plugin manifests and every version-bearing text file via npm run bump, writes the CHANGELOG entry, re-validates, then commits, pushes to main, tags, and publishes the GitHub release. Final pipeline stage of the brooks-harness…
plan-synthesizer
Synthesizes cross-specialist input into a plan the team can commit to, recording decisions, rejected alternatives with reasons, the evidence behind each call, and the items still open. Reads the inputs from every specialist who contributed, reconciles their recommendations, and applies an evidence standard to each …
pr-creator
Use for creating and editing pull requests via gh pr create, gh pr edit, gh pr view, gh pr diff, and gh pr list. Does NOT merge or mark ready (use pr-merger for that). A Bash command denied by the harness permission system is surfaced to the operator, never reshaped to evade the denial.
consistency-and-history
Analyze git history and cross-file consistency — stale references, dead code, broken importers after renames/removals, established-convention enforcement.
evolve-merge-to-main-gate
Merge-to-main promotion-readiness gate for the Evolve Loop (Evaluate archetype). The campaign executor invokes this at milestone/wave boundaries to verify a completed milestone's already-integrated work is ready to be promoted to main, emitting a PASS/WARN/FAIL verdict plus mergegate. signals. READ-ONLY — it never…
cad-reviewer-low
The low rung of cad-reviewer; bin/route.mjs picks it, not the user.