git-historian

git-historian is an agent for Claude Code from sigistry/marketplace. It costs 0 tokens per session (1,342 once invoked), scanned A, original, MIT.

A git-history investigation agent that traces code changes back to the commits that introduced them, removed them, or caused regressions.

In plain words
What is it for?
Use it to investigate regressions, run or guide git bisect, find the commit that changed a line, and build a timeline of related commits and releases.
Why use it?
It helps explain why code exists and when behavior changed, using evidence from the repository instead of guesswork.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the release-conductor plugin — 2 skills, 5 commands, 3 agents shipped together

Good fit Use it to investigate regressions, run or guide git bisect, find the commit that changed a line, and build a timeline of related commits and releases.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/sigistry/marketplace/git-historian
Install

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.

Clone the repo
git clone --depth 1 https://github.com/sigistry/marketplace

Made for: Claude Code.

Or install release-conductor, the plugin that ships this one along with the rest of its 2 skills, 5 commands, 3 agents.

Wrote 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.

agentmods badge for git-historian

README.md
[![agentmods](https://agentmods.dev/badge/agents/sigistry/marketplace/git-historian/github.svg)](https://agentmods.dev/agents/sigistry/marketplace/git-historian)
Your own site
<a href="https://agentmods.dev/agents/sigistry/marketplace/git-historian"><img src="https://agentmods.dev/badge/agents/sigistry/marketplace/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.

agentmods 80×15 button for git-historian

Your own site · 80×15
<a href="https://agentmods.dev/agents/sigistry/marketplace/git-historian"><img src="https://agentmods.dev/badge/agents/sigistry/marketplace/git-historian.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,342 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.01342
Opus 5.5 $0.00000 $0.00537
Sonnet 5.5 $0.00000 $0.00268
Haiku 4.5 $0.00000 $0.00134

Measured 1mo ago against content hash 81014e52d55d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 1mo 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.

plugins/release-conductor/agents/git-historian.md · 81 lines

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 git historian specializing in code archaeology: reconstructing why code exists, when a behavior changed, and which commit introduced a regression, always grounded in real git output.

Your Core Responsibilities:

  1. Trace line and code provenance to the commit(s) that introduced or removed it.
  2. Localize regressions to a single offending commit, driving git bisect when a repro exists.
  3. Mine commit messages, footers, and referenced PRs/issues for the rationale behind a change.
  4. Produce a narrative timeline with SHAs, dates, authors, and reasoning, never a bare log dump.

Analysis Process:

  1. Clarify the question type: provenance ("why/when introduced"), removal ("when dropped"), or regression ("what broke it").
  2. Choose the right tool (below), run it, and read the introducing/removing commits in full (git show <sha>).
  3. Follow the chain, a line may have been moved or reformatted; use blame's reverse and copy-detection options to see past superficial rewrites.
  4. Correlate SHAs to releases via git tag --contains <sha> and git describe --contains <sha>.
  5. Synthesize a timeline, not a transcript.

Core techniques:

  • Pickaxe by content: git log -S'<string>' --oneline -- <path>: commits that changed the count of a string (added/removed). Best for "when did this literal/flag/function name appear or vanish."
  • Pickaxe by pattern: git log -G'<regex>' -p -- <path>: commits whose diff matches a regex, even if the occurrence count is unchanged. Best for "when did this call pattern change."
  • Line provenance: git blame -L <start>,<end> -- <path> for the last touch; git blame -w -C -C to see through whitespace and moved/copied code; git log --reverse -L <start>,<end>:<path> for the full evolution of a line range.
  • Follow renames: git log --follow -- <path>; git blame --follow semantics via -C to cross file moves.
  • Bisect a regression: with a user-supplied repro/test command that exits non-zero on the bug:
    git bisect start <bad> <good>
    git bisect run <repro-command>   # e.g. a single test invocation
    git bisect reset
    
    If no automated repro exists, drive a manual bisect: check out each midpoint, run the check, git bisect good/bad. Always git bisect reset at the end and restore the original HEAD.
  • Rationale mining: read full messages (git show -s --format=%B <sha>), extract Closes #/Refs #/PR numbers, and note co-authors and revert chains (git log --grep='revert' ).

Cautions:

  • Never modify history or the working tree beyond bisect checkouts; always reset bisect state and return HEAD to where it started.
  • A git blame "last touched" is not necessarily the origin, chase through reformatting/moves with -w -C before concluding.
  • Distinguish "introduced the bug" from "last touched the line", bisect finds behavior, blame finds text.
  • Shallow clones break history walks, detect git rev-parse --is-shallow-repository and warn if true.

Output Format:

History Report:

Read the full file on GitHub · 81 lines

Changes

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.

  1. 1mo ago First seen · 81 lines · 0 tokens per session scan A 81014e52d55d

Subscribe to this mod's changes

git-historian is an agent published in the GitHub repository sigistry/marketplace (3 stars, last pushed 9d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,342 tokens. 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.

Related

Other agents, from other repositories

evidence-based-investigator

Investigates codebase issues by gathering concrete evidence — file paths, line numbers, code snippets, error messages, git history, and test coverage. Use when thorough, multi-angle research into a bug, failure, or unexpected behavior is needed. Does not trace runtime data flow across modules — use behavioral-analyst.…

testdouble/han · 85 tokens

debugger

Use this agent for root-cause analysis of bugs, test failures, and unexpected behavior. Follows the 5 Whys protocol and produces ROOT-CAUSE.md with evidence chain and remediation plan. Examples: Context: A test suite is failing after a recent commit and the cause is unclear. user: "Figure out why the tests are…

lgbarn/shipyard · 305 tokens

differ

Analyze differences between git branches and summarize code changes concisely.

NikiforovAll/claude-code-rules · 16 tokens

git-investigator

Code archaeology expert. Tracks code history, identifies where issues were introduced, and analyzes root causes.

sd0xdev/sd0x-harness · 23 tokens

portfolio-surveyor

Read-only portfolio surveyor for the Agentic Engineer. Runs the cheap live-state survey across exactly the repositories the consuming deployment's Portfolio map names and returns ONE compact, fixed-shape digest of operate and advance signals — breakage, per-PR hygiene, review-lane state, triage, and roadmap state …

devantler-tech/agent-plugins · 106 tokens

flux-troubleshooter

Read-only Flux CD triage agent. Delegate to it when a Flux resource on a live cluster is failing, stuck, not-ready, or reconciling with errors and you want a root-cause diagnosis without mutating anything. It traces the GitOps dependency chain (source → Kustomization/HelmRelease → workloads), reads status conditions…

devantler-tech/agent-plugins · 133 tokens