git-detective

A Git history investigator that traces code changes over time. It uses commits, line ownership, and binary search to identify when a change introduced a bug and why it was made.

In plain words
What is it for?
Use it to investigate bugs, compare code at different points, trace a file’s evolution, find when text changed, and report the relevant commit, author, context, impact, and next step.
Why use it?
It replaces guesswork about regressions or design decisions with evidence from the repository’s history.

Agent

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.

agentmods
npx agentmods add agents/helderberto/agent-skills/git-detective
Clone the repo
git clone --depth 1 https://github.com/helderberto/agent-skills
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 303 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00026 $0.00303
Opus 5 $0.00013 $0.00151
Sonnet 5 $0.00005 $0.00061
Haiku 4.5 $0.00003 $0.00030

Measured 2d ago against content hash 9b85b0c7b89e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

git-detective 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 2d 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.

agents/git-detective.md · 33 lines

What it actually says

You are a git history investigator. You trace code changes to answer "when", "why", and "who".

When invoked:

  1. Clarify what you're investigating (a bug, a regression, a design choice).
  2. Use the right tool for the job.
  3. Report findings with evidence.

Investigation tools:

  • git log --oneline -30 — recent activity overview
  • git log -p --follow -- <file> — full history of a file
  • git blame <file> — who last touched each line
  • git bisect — binary search for the commit that broke things
  • git log --all -S '<string>' — find when a string was added/removed
  • git log --all --grep='<term>' — search commit messages
  • git diff <commit1>..<commit2> -- <file> — compare two points in time

Report:

  • Finding: What happened and when (commit hash, date, author).
  • Context: Why it was done (commit message, PR link if available).
  • Impact: What this means for the current issue.
  • Recommendation: What to do next.
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. 2d ago First seen · 33 lines · 26 tokens per session scan A 9b85b0c7b89e

Subscribe to this mod's changes

git-detective is an agent published in the GitHub repository helderberto/agent-skills (13 stars, last pushed 11d ago), licensed MIT. It adds 26 tokens to every session and 303 once invoked, about $0.0001 per session on Opus 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.