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 askgit 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/ask)<a href="https://agentmods.dev/skills/mimfort/rag_for_git/ask"><img src="https://agentmods.dev/badge/skills/mimfort/rag_for_git/ask/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/ask"><img src="https://agentmods.dev/badge/skills/mimfort/rag_for_git/ask.svg" alt="Reviewed on agentmods" width="80" 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 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 22 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.
- medium MCP Rug Pull · line 39 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
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 | $0.00100 | $0.01531 |
| Opus 5.5 | $0.00040 | $0.00612 |
| Sonnet 5.5 | $0.00020 | $0.00306 |
| Haiku 4.5 | $0.00010 | $0.00153 |
Grade A, and why
ask 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ask (codebase Q&A)
Answer a free-text question about the codebase with a grounded response: every claim is
backed by a real path:line citation, never an invented path. Built on the reviewer MCP server
(hybrid RAG + code graph). This skill reads and explains; it does NOT modify code or review PRs.
Always answer the user in Russian (the project language), regardless of this file's language.
Tool calls, code identifiers, and path:line citations stay verbatim.
Inputs
$ARGUMENTS — a free-text question about the code (e.g. "where is authentication",
"how does index freshness work", "explain the retrieval pipeline").
Tools
Use the session-less tools above.
Plus the harness file tools (Read, Grep, Glob) to read source from the local clone on disk.
Pipeline
- Resolve repo/branch.
repo:git remote get-url origin→ strip a trailing.git, take the last two path segments (owner/name). Pass""to let the server useDEFAULT_REPOif origin is missing.branch:
Freshness check (first code question of the session only). After resolving repo/branch and
ONLY on the first code question in this conversation — rely on conversation memory: if you have
already checked index freshness earlier in this session, skip this — run
uvx --from rag-reviewer reviewer status <path> --branch <branch> --json and read drift. If
drift > 0, emit exactly one banner line, in Russian:
«⚠ индекс отстаёт на N коммитов, ответ может не учитывать свежие изменения → rag-reviewer:sync-codebase».
Do NOT block, reindex, ask for confirmation, or call sync_board — this is warn-only. Cost ≈ 0
Voyage (reads index_meta + local git). Fail-open: any error → skip the banner silently
(Q&A is latency-sensitive).
1.5. Subsystem prior (cheap, optional). Call get_subsystem_summaries(repo, branch, query="<the user's question>").
At scale (summary count above the deploy threshold) this returns the top-k subsystems nearest the
question; on small repos it returns all (back-compat). If it returns summaries, use the one matching
the question's subsystem as a high-level orientation before search_codebase — this cuts
exploration steps for architectural / "how does subsystem X work" questions. The summary is only a
prior: every path:line you cite in the answer still comes from real code (search_codebase /
Read), never from the summary text.
Fail-open: empty / unavailable → skip this step and proceed exactly as before.
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 · 107 lines · 100 tokens per session scan A 1724fcce2cdb
ask is a skill published in the GitHub repository mimfort/rag_for_git (20 stars, last pushed 6d ago), licensed MIT. It adds 100 tokens to every session and 1,531 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
code-knowledge-graph
Codebase'i knowledge graph olarak analiz et. Dependency, call graph, hotspot analizi.
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…
coograph-review
Strict read-only review of the current changes for spec compliance, convention violations, logic bugs, and architecture. Every finding cites a verbatim quote from a fresh file read. Use after implementation, before declaring done.
graphenium
Use when analyzing codebase structure, verifying pre-flight policy compliance, tracing transitive dependency closures, or auditing post-edit scope creep.
celmis-search
Search and read code through Celmis instead of grepping or cat-ing whole repositories. Use when you need where a symbol is defined, who calls it, what a file or module contains, how another service does something ("make a DB connection like in service X", "do authorization the way service X does", "how does X load its…
autoreview
Structured code review through the shared OpenClaw agent-skills installation.