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 OutlineDriven/odin-claude-plugin --skill git-history-analysisgit clone --depth 1 https://github.com/OutlineDriven/odin-claude-pluginWrote 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/outlinedriven/odin-claude-plugin/git-history-analysis)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/git-history-analysis"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/git-history-analysis.svg" alt="Measured on agentmods" 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 | $0.00040 | $0.01351 |
| Opus 5 | $0.00020 | $0.00675 |
| Sonnet 5 | $0.00008 | $0.00270 |
| Haiku 4.5 | $0.00004 | $0.00135 |
Grade A, and why
git-history-analysis 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.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git history analysis
Contract
| Field | Bound contract |
|---|---|
| Trigger | User asks about recent engineering work, what the team is working on, or planning or roadmap preparation. |
| Authority | Human-gated: previews the Slack destination and posting consequence before the optional remote Slack post; otherwise reversible local: writes only a report under reports/git_history_analysis/; rollback is deleting the report. No remote mutation. No force-push or PR creation. |
| Side effect | Writes a categorized commit-breakdown report to reports/git_history_analysis/. Optionally posts a summary to Slack only on explicit human confirmation. |
| Done | Report saved with commit breakdown, active branches, key insights, risks, and follow-up questions. |
Inputs
- Repository path: required. Defaults to the current working directory when omitted. Only analyze the user's application repositories; do not analyze this agent's own repository.
- Time period: optional. Defaults to the last 2 weeks (14 days).
- Filters: optional path or branch filters to narrow the scope.
Procedure
- Bind scope before mutation: confirm the repository path and time period. If the path is ambiguous or absent and no default is acceptable, stop and ask; do not guess. Done when: the repository path and time period are confirmed, or the run stopped to ask.
- Verify the path is a git repository with commits in the requested range. If not, stop and report the blocker; do not write a partial report. Done when: the path is a git repository with commits in range, or the run stopped with the blocker reported.
- Collect commit history from the repository root, adjusting
--sinceto the requested period and appending-- <filters>when path filters are specified:
Omitgit --no-pager log --since="2 weeks ago" --pretty=format:"%h|%ad|%s" --date=short --stat -- <filters>-- <filters>when no path filters are supplied. Done when: commit history collected for the requested period from the repository root. - Collect active branches (work in progress), filtering out merged branches and dynamically resolving the default branch instead of hardcoding
main:
Apply branch-name filters beforedefault_branch=$(git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's@^refs/remotes/origin/@@' || echo main) git --no-pager branch -r --no-merged origin/$default_branch --sort=-committerdate | grep -E "<filters>" | head -20headso filtering cannot discard branches beyond the first twenty. Path filters are a different concern: collect them withgit log --all --oneline -- <paths>in their own step, never by grepping branch names. Done when: active unmerged branches listed, sorted by most recent commit. - Collect recent merges to the default branch (completed work), dynamically resolving the default branch and appending
-- <filters>when path filters are specified:
Omitdefault_branch=$(git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's@^refs/remotes/origin/@@' || echo main) git --no-pager log --since="2 weeks ago" --merges --pretty=format:"%h|%ad|%s" --date=short origin/$default_branch -- <filters>-- <filters>when no path filters are supplied. Done when: recent merges to the default branch collected for the requested period. - Categorize commits by conventional-commit prefix:
feat:features,fix:bug fixes,refactor:code improvements,docs:documentation,test:testing,chore:maintenance. Adapt the prefix set when the repository uses different conventions. Done when: every commit is categorized by prefix (adapted to the repo's conventions). - Group commits by directory or component to identify the most active areas. Done when: commits grouped by directory/component with active areas identified.
- Surface patterns: which features receive the most attention, whether any area shows high bug-fix activity, and the balance between new features and maintenance. Done when: patterns surfaced across features, bug-fix activity, and feature/maintenance balance.
- Note in-progress work from active branches not yet merged to the default branch. Done when: in-progress work from unmerged active branches noted.
- Do not attribute work to individuals. Omit author names from the report; describe work by branch, component, and commit type. Done when: the report contains no author names; work described by branch, component, and commit type.
- Write the report to
reports/git_history_analysis/git_analysis_YYYY-MM-DD.mdusing the Output format. Done when: the report file exists at the dated path using the Output structure. - If the user explicitly requests a Slack summary, confirm the destination and post only after explicit human confirmation. This branch is optional and is not required for the done predicate. Done when: a Slack summary is posted only after explicit human confirmation, or the branch is skipped.
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.
- 2d ago First seen · 64 lines · 40 tokens per session scan A 73315121f3f2
git-history-analysis is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed yesterday), licensed Apache-2.0. It adds 40 tokens to every session and 1,351 once invoked, about $0.0002 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 2026-09-06.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…