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 mimfort/rag_for_git --skill pr-walkthroughgit clone --depth 1 https://github.com/mimfort/rag_for_gitWrote 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/mimfort/rag_for_git/pr-walkthrough)<a href="https://agentmods.dev/skills/mimfort/rag_for_git/pr-walkthrough"><img src="https://agentmods.dev/badge/skills/mimfort/rag_for_git/pr-walkthrough/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/mimfort/rag_for_git/pr-walkthrough"><img src="https://agentmods.dev/badge/skills/mimfort/rag_for_git/pr-walkthrough.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 12 Skill instructs the agent to never refuse or to always comply. Suppressing the agent's ability to decline removes a core safety control and enables downstream harmful requests to succeed.Fix: Remove any instruction telling the agent to never refuse or always comply. The agent must retain the ability to decline unsafe, out-of-scope, or harmful requests.
- high Prompt Injection · line 17 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00094 | $0.00824 |
| Opus 5.5 | $0.00038 | $0.00330 |
| Sonnet 5.5 | $0.00019 | $0.00165 |
| Haiku 4.5 | $0.00009 | $0.00082 |
Grade A, and why
pr-walkthrough 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.
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.
PR walkthrough (reading guide for a human reviewer)
Help a human reviewer orient in a PR — not find bugs. Produce a markdown guide: where to start
(by centrality), what each file changes, and what it impacts ("careful, affects X"). Separate from
bug findings (review-pr).
Always answer the user in Russian (the project language). Tool calls, identifiers and path:line
stay verbatim.
Tools
Plus the PR-session tools (reviewer MCP): prepare_review, get_impact, get_changed_file_diff,
find_callers, get_related_symbols, read_file; optional get_subsystem_summaries (PRI-159);
optional post_pr_walkthrough (only on explicit user request).
Pipeline
-
Resolve repo & prepare the session. Resolve
repo(git remote). Callprepare_review(repo, pr). If it returns{"status": "skipped"}(branch not in REVIEW_BRANCHES), tell the user (in Russian) and stop. -
Reading order (centrality). Call
get_impact(repo, pr)→ changed symbols and their callers. Order "start here" by how much depends on each changed symbol (most central first). Graph down → fall back to ordering by file (fail-open). -
What each file changes. For each changed file,
get_changed_file_diff(repo, pr, path)→ one line describing what it changes. -
Impact ("careful, affects X"). For the central changed symbols,
find_callers/get_related_symbols→ who depends on them. Every "affects X" must be backed by a real caller. -
Subsystem prior (optional).
get_subsystem_summaries(repo, pr.base_ref, query="<PR title + changed file paths>")→ name the touched subsystem(s) in one line. Pass the PR's target branchpr.base_ref(from theprepare_reviewresponse), NOT the local git branch — subsystem summaries are indexed per target branch (base:<branch>). Empty / unavailable → skip (fail-open). -
Assemble the guide (Russian markdown):
- Начни отсюда — ordered list (most central first).
- По файлам — one line per changed file.
- Осторожно, влияет на — impacted symbols + their callers.
- (optional) Подсистемы — 1–2 lines from summaries.
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.
- 1mo ago First seen · 64 lines · 94 tokens per session scan A 02e233650896
pr-walkthrough is a skill published in the GitHub repository mimfort/rag_for_git (20 stars, last pushed 6d ago), licensed MIT. It adds 94 tokens to every session and 824 once invoked, about $0.0004 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 skills, from other repositories
pr
Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.
otto-pr-review-loop
Run Polly and OCR on a PR until all findings settle.
engram-branch-pr
PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.
github-contributor
A step-by-step guide for contributing code, tests, documentation, or build changes to open-source projects you do not maintain. It explains how to prepare a pull request that follows the project’s rules and is easier for maintainers to review.
revdiff
Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…