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 configure-reviewgit 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/configure-review)<a href="https://agentmods.dev/skills/mimfort/rag_for_git/configure-review"><img src="https://agentmods.dev/badge/skills/mimfort/rag_for_git/configure-review.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 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 8 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.
- medium Rogue Agent · line 17 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 69 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00035 | $0.03425 |
| Opus 5 | $0.00017 | $0.01713 |
| Sonnet 5 | $0.00007 | $0.00685 |
| Haiku 4.5 | $0.00003 | $0.00343 |
Grade A, and why
configure-review 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 8d 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 — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Configure Review
Always answer the user in Russian. Update only the requested policy values; Never clobber foreign
keys such as categories. This skill is standalone: no reviewer MCP, database, or board connection
is required for the baseline.
Scope
Manage summary_cluster_depth, summary_cluster_depth_overrides, summary_topk_threshold,
summary_paths.ignore, paths.ignore, context_limits, and the optional task_board block,
including its generic sync_filter. An empty task_board: disables the board for this repository. Never read, request,
display, or write credential values in either policy target.
Tracked branches are separate from review policy. Manage repository.primary_branch and
repository.index_branches only in the home per-repo target. The committed .review.yml cannot
own repository, because branch selection must be available before a committed ref can be read.
Untracked .venv, node_modules, __pycache__, dist, and build are gitignored and never
enter the index. Do not use a filesystem walk to find them.
Safe YAML preflight
Inspect each selected policy or home YAML file with a local boolean-only process.
Run this preflight before any tool call that can return file contents.
Return only safe/blocked, never matching lines, values, or exception text. Do not use Read or Grep
to perform this preflight. The process must reject non-regular or symlinked files, malformed or
non-mapping YAML, and credential-like keys at any depth. Also reject duplicate mapping keys,
including duplicate repository keys and duplicate branch fields. Reject anchors, aliases, and merge keys.
Reject these cases before reading or mutating the file in model context.
Only after a safe result may a content-returning tool read the file for a line-oriented edit.
For a home target, derive the canonical home config root lexically even when it does not exist. Check every existing parent path component through the destination without following symlinks; reject symlinks and non-directories. Missing destinations, including a missing home config root, are allowed only when the nearest existing parent is a real directory and the normalized destination remains inside the canonical home config root. After creating any missing directories, run the path preflight again. Also re-check immediately before writing so a changed path never inherits an earlier safe result.
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.
- 8d ago First seen · 259 lines · 35 tokens per session scan A 16edbf0f662f
configure-review is a skill published in the GitHub repository mimfort/rag_for_git (21 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 3,425 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 2026-08-30.
Other skills, from other repositories
m1nd-first
Use when investigating a repository, searching for implementation, reviewing changes, working from specs/docs, or preparing a risky code change in an environment where m1nd is available. This doctrine makes m1nd the first investigative layer before grep, glob, or manual file reads, except when the task is pure…
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
security-review
Perform a focused security review of pending git changes to identify high-confidence security vulnerabilities with real exploitation potential. Use this skill when the user asks for a security review, security audit, vulnerability scan, or wants to check pending changes on a branch for security issues before merging.…
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.
feature-dev
Guide a feature implementation through a structured seven-phase workflow with deep codebase understanding, clarifying questions, parallel architecture design, and quality review. Use this skill when the user asks to build a new feature, add functionality, or wants a methodical approach to implementation rather than…
reply-to-pr-threads
Draft, confirm, and post replies to GitHub PR review threads. Handles per-category reply formatting, re-fetches thread resolution state so auto-resolved threads are skipped, and posts via GraphQL. Use when the user asks to "reply to PR threads", "post PR thread replies", or "draft PR reply messages".