Borrowing it
Nothing to install: this file belongs to stellar-experimental/stellar-raven. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/stellar-experimental/stellar-raven/main/.agents/skills/retrieval-system-audit/SKILL.mdgit clone --depth 1 https://github.com/stellar-experimental/stellar-ravenWrote 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/stellar-experimental/stellar-raven/retrieval-system-audit)<a href="https://agentmods.dev/skills/stellar-experimental/stellar-raven/retrieval-system-audit"><img src="https://agentmods.dev/badge/skills/stellar-experimental/stellar-raven/retrieval-system-audit/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/stellar-experimental/stellar-raven/retrieval-system-audit"><img src="https://agentmods.dev/badge/skills/stellar-experimental/stellar-raven/retrieval-system-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.01142 |
| Opus 5.5 | $0.00026 | $0.00457 |
| Sonnet 5.5 | $0.00013 | $0.00228 |
| Haiku 4.5 | $0.00007 | $0.00114 |
Grade A, and why
retrieval-system-audit 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Retrieval System Audit
Measure the complete retrieval system before changing it. Ship only general improvements that survive real endpoint calls and reviewed golden questions.
Use the companion runbooks
- Read
PLAN.md,ARCHITECTURE.md,eval/EVALS.md, andeval/qa/README.md. - Use the global
herdrskill to run an explicitly requested multi-model audit, one agent per pane. - Use
run-evalsfor every evaluation run and spend decision. - Use
golden-truthbefore changing a golden question or answer. - Use
improvements-pipelinefor verified upstream defects. - Use
live-drift-resolutionfirst when the committed catalog differs from the live surfaces.
Keep fixed boundaries
- Treat the manifest as the exposed surface.
- Keep exact operation and skill identifiers.
- Keep data, soft-empty, and error responses distinct.
- Keep secrets and service traffic outside model-authored code.
- Do not call a paid or side-effecting service operation during inventory work.
- Do not tune production behavior for one question.
- Prefer deletion, simpler descriptions, and existing interfaces before new code.
- Keep raw paid results local and gitignored.
- Give Git, spending, deployment, and external filing authority to the coordinator.
Run the audit
1. Isolate and pin
Create a dedicated Git worktree and a round ledger under .agents/rounds/. Record the revision, clean-tree digest, manifest digest, runner digest, corpus digest, and evaluation gates.
Run the free baseline from AGENTS.md. Compile generated artifacts and verify that regeneration leaves the tree clean.
2. Build one surface ledger
Inventory every exposed operation and whole skill. Compare the committed manifest, generated specification, adapters, live catalog, and fresh-client MCP descriptions.
Record each input schema, output schema, retrieval description, retrieval profile, response class, authority scope, safety class, and evaluation coverage. Use references/evidence-contract.md for the required fields.
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.
- 1mo ago First seen · 104 lines · 66 tokens per session scan A a9aed944c373
retrieval-system-audit is a skill published in the GitHub repository stellar-experimental/stellar-raven (13 stars, last pushed yesterday), licensed Apache-2.0. It adds 66 tokens to every session and 1,142 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 2026-08-31.
Other skills, from other repositories
mcp-apps-builder
MANDATORY for ALL MCP server work - mcp-use framework best practices and patterns. READ THIS FIRST before any MCP server work, including: Creating new MCP servers Modifying existing MCP servers (adding/updating tools, resources, prompts, widgets) Debugging MCP server issues or errors Reviewing MCP server code for…
mcp-builder
DEPRECATED: This skill has been replaced by mcp-app-builder. Check if mcp-app-builder is available in the skills folder. If not, install it: npx skills install mcp-use/mcp-use --skill mcp-app-builder Use mcp-app-builder instead of this skill. Build Model Context Protocol (MCP) servers with mcp-use framework. Use when…
thinking-out-loud
A contract for what the agent does when a long, messy, stream-of-consciousness ramble arrives (usually voice dictation): act on nothing until the echo brief is approved. The echo audits the entire transfer, mission, locked decisions and constraints, open questions, flips and parked tangents, with the model's…
hugging-face-evaluation
Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, importing scores from Artificial Analysis API, and running custom model evaluations with vLLM/lighteval. Works with the model-index metadata format.
hugging-face-model-trainer
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV…
hugging-face-datasets
Create and manage datasets on Hugging Face Hub. Supports initializing repos, defining configs/system prompts, streaming row updates, and SQL-based dataset querying/transformation. Designed to work alongside HF MCP server for comprehensive dataset workflows.