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 sync-codebasegit 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/sync-codebase)<a href="https://agentmods.dev/skills/mimfort/rag_for_git/sync-codebase"><img src="https://agentmods.dev/badge/skills/mimfort/rag_for_git/sync-codebase/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/sync-codebase"><img src="https://agentmods.dev/badge/skills/mimfort/rag_for_git/sync-codebase.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
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 →
- medium MCP Rug Pull · line 42 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
- medium MCP Rug Pull · line 52 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 | $0.00066 | $0.00907 |
| Opus 5.5 | $0.00026 | $0.00363 |
| Sonnet 5.5 | $0.00013 | $0.00181 |
| Haiku 4.5 | $0.00007 | $0.00091 |
Grade A, and why
sync-codebase 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sync Codebase
Builds or updates the reviewer base index — vector embeddings (Postgres/pgvector) and code graph
(Neo4j) — from a local repo clone using reviewer index. This is a one-time setup operation;
subsequent runs are incremental (only changed files are re-embedded).
Inputs
Parse from $ARGUMENTS (all optional):
--path <path>: path to the local repo clone. Default: current working directory.--ref <branch>: git ref to index. Default:main.--repo <owner/name>: repo identifier for multi-repo setups. If omitted, derived automatically fromgit remote get-url origin.--backend <auto|scip|treesitter>: graph backend override. Default:auto(SCIP if in PATH, else tree-sitter).
Pipeline
-
Resolve inputs. If
--pathnot given, use the current working directory. If--refnot given, usemain. If--reponot given, run:git -C <path> remote get-url originStrip
.gitsuffix, extract the last two path segments (owner/name). -
Check prerequisites. Verify:
uvxis available:uvx --versionsucceeds.- The path is a git repo:
git -C <path> rev-parse --git-dirsucceeds. - The reviewer MCP server is reachable (run
reviewer checkor confirm the user has.envconfigured withPG_DSN,NEO4J_URI,VOYAGE_API_KEY). - Docker services are up if using the default stack:
docker compose psshowsparadedbandneo4jrunning. - Stop and tell the user what is missing if any check fails.
-
Run indexing.
uvx --from rag-reviewer reviewer index <path> --ref <ref>Add
--repo <owner/name>if resolved or provided. Stream the output to the user.Expected duration: seconds for small repos, minutes for large ones — Voyage free tier (3 RPM / 10K TPM) causes throttling with automatic retry/backoff. That is normal, not an error. Use
--limit N(if supported) for a quick smoke run. -
Verify. After indexing completes, optionally run a diagnostic search to confirm the corpus:
uvx --from rag-reviewer reviewer search "your query here"Or call
search_codevia the reviewer MCP tools directly.
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 · 74 lines · 66 tokens per session scan A 884a04898822
sync-codebase is a skill published in the GitHub repository mimfort/rag_for_git (20 stars, last pushed 6d ago), licensed MIT. It adds 66 tokens to every session and 907 once invoked, about $0.0003 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
advisor-orchestrator-worker
Use when a task is too large for one model pass, needs parallel research or generation across many subtasks (like researching a dozen competitors at once), or the user asks to orchestrate multiple models, split work across a model team, run an advisor-worker loop, have a stronger model review the plan while cheap…
rag-code-review
When performing code review on a PR, diff, snippet, or "look at this change" request, first consult the corpus for related ADRs, coding standards, prior patterns, and similar files. Grounds review comments in the team's actual decisions instead of generic best practices. Trigger on any review-style request — "review"…
rag-techniques-contribution-guidelines
Checks a RAGTechniques pull request against the repository's contribution guidelines (CONTRIBUTING.md): where new technique notebooks go, the README list entry and table row every new technique needs, the required notebook structure, and notebook hygiene. Use on any PR that adds or changes a notebook under…
world-model-diagnostic
Twenty-minute diagnostic mapping a team to a world-model paradigm (vector DB, structured ontology, signal-fidelity). Use when you say "run the world model diagnostic", "audit our world model", "which world model architecture fits us", or "audit where we automate judgment". Use for AI readiness assessments and…
answer-audit
Adversarially audit a RAG answer against the corpus it claims to cite. Use when asked to review, critique, sanity-check, or "give skeptical feedback on" an answer produced by Canon (or any retrieval-grounded system) — especially when the answer looks good. Assumes the answer is wrong until each claim is proven…
x-bug2rag
A knowledge-capture tool that turns reusable bug explanations into a local RAG collection, meaning a searchable store of text that an agent can retrieve later. It records the trigger, incorrect implementation, correct implementation, and observable difference.