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 olehsvyrydov/AI-development-team --skill answer-auditgit clone --depth 1 https://github.com/olehsvyrydov/AI-development-teamWrote 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/olehsvyrydov/ai-development-team/answer-audit)<a href="https://agentmods.dev/skills/olehsvyrydov/ai-development-team/answer-audit"><img src="https://agentmods.dev/badge/skills/olehsvyrydov/ai-development-team/answer-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/olehsvyrydov/ai-development-team/answer-audit"><img src="https://agentmods.dev/badge/skills/olehsvyrydov/ai-development-team/answer-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 | $0.00078 | $0.01481 |
| Opus 5.5 | $0.00031 | $0.00592 |
| Sonnet 5.5 | $0.00016 | $0.00296 |
| Haiku 4.5 | $0.00008 | $0.00148 |
Grade A, and why
answer-audit scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`chunks` table. Neither container has curl; use bash `/dev/tcp` from the api container. How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Answer Audit — skeptical review of a grounded answer
A RAG answer that is fully citation-grounded can still be materially wrong. Every claim can trace to a real passage while the values inside those claims are silently corrupted in transit. This skill exists because a confident, well-structured, 100%-grounded answer is the hardest kind to catch — the citations create trust the content has not earned.
Default posture: the answer is guilty until proven innocent. Do not grade it on how it reads. Grade it on whether each atom survives a character-level diff against its source.
The rule that matters
Grounded ≠ accurate. Citation presence is not citation support.
Most RAG guardrails ("no sources → no answer", "cite every claim") only prove a passage was retrieved. They do not prove the passage says what the answer says it says. Audit the gap.
Method
Never audit from memory or from the model's own citation list. Go to the corpus.
- Pull the corpus the answer was drawn from (see Canon commands below). Get the raw chunk text, not a summary of it.
- Atomise the answer. Extract every checkable atom: figures, currencies, units, percentages, thresholds, dates, proper nouns, and any quoted phrase.
- Verify each atom verbatim. Regex/grep the corpus for the exact token. An atom that does not
appear verbatim is a finding, even if a similar one does.
$300kand£300kare different facts. - Diff the source passage against the answer's rendering of it, sentence by sentence, for the passages that carry the answer's most consequential claims. This is where the real damage hides — step 3 alone will not catch a dropped caveat.
- Hunt for what is missing, not just what is wrong. Omission is the most under-detected failure mode and the most dangerous, because nothing in the output signals it.
- Check the telemetry — which model tier answered, how many attempts, how many passages were stuffed into the prompt. Compression pressure predicts distortion: many passages + a weak tier is the setup for exactly these errors.
- Report defects with the source text quoted beside the answer text. Never assert a defect you have not shown.
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 · 94 lines · 78 tokens per session scan A 6dc0f3ebc7e6
answer-audit is a skill published in the GitHub repository olehsvyrydov/AI-development-team (17 stars, last pushed 5d ago), licensed MIT. It adds 78 tokens to every session and 1,481 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
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.
x-dev-rag-call
A local semantic search tool that finds relevant passages in specified Markdown or text files. It uses an embedding model, which represents meaning as numbers, to return the closest passages for a question or plan.
rag-design
Retrieval-Augmented Generation (RAG) system design — chunking, embeddings, vector storage, hybrid retrieval, reranking, evaluation, grounding, and the RAG-vs-fine-tune-vs-long-context decision. Auto-fires when the work touches RAG pipelines, vector databases, embeddings, semantic search, document grounding, or…
qdrant
Vector search engine for production RAG systems.
chroma
Embedding database for RAG and semantic search.
pinecone
Managed vector DB for production RAG and search.