Borrowing it
Nothing to install: this file belongs to nacre-work/nacre. 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/nacre-work/nacre/main/.claude/skills/audit-event/SKILL.mdgit clone --depth 1 https://github.com/nacre-work/nacreWrote 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/nacre-work/nacre/audit-event)<a href="https://agentmods.dev/skills/nacre-work/nacre/audit-event"><img src="https://agentmods.dev/badge/skills/nacre-work/nacre/audit-event.svg" alt="Measured on agentmods" 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 | $0.00077 | $0.00941 |
| Opus 5 | $0.00039 | $0.00470 |
| Sonnet 5 | $0.00015 | $0.00188 |
| Haiku 4.5 | $0.00008 | $0.00094 |
Grade A, and why
audit-event 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 6d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adding an audit event
Contract: docs/audit.md. The audit log is a product feature, not a debug log —
"show me which documents your agent read last quarter" has to get a precise
answer, which means completeness matters more than volume.
Always recorded
Every search with the doc_id list it returned; every document access; every
grant issued and revoked; every login and token issue; every organization
configuration change; every reindex start; every denial.
Denials are the most useful lines in the file and the easiest to miss, because
the code path producing one is usually an early return. If you add a branch that
refuses access — including one that surfaces as 404 on the wire — it writes an
event with result: "deny".
Never recorded
Document contents. Chunk text. Full query text unless
NACRE_AUDIT_QUERY_TEXT=true; the default stores query_hash instead, which is
enough to investigate an incident and not enough to leak through the journal.
An audit log that leaks what it is auditing is worse than none, because it is retained for 400 days by default and exported to a SIEM.
Shape
{
"org_id": "uuid",
"actor": { "type": "service_account", "id": "uuid", "label": "svc-support-bot" },
"surface": "mcp", // api | mcp | admin | system
"client": "claude-code/2.1", // from the client's _meta
"action": "search",
"target": { "layers": ["contracts"], "returned_docs": ["uuid"], "top_k": 10 },
"result": "allow", // allow | deny | error
"detail": { "query_hash": "sha256:…", "latency_ms": 128, "acl_version": 42 },
"request_id": "01JQ8…"
}
request_id is mandatory and matches the field in the HTTP error body and the
OpenTelemetry trace. That correspondence is the whole investigative story; an
event without it is close to useless.
Ordering
Write the event before the response goes out. A lost event is worse than a
slow response. Do not move the write into a fire-and-forget background task to
save latency — if that is genuinely needed, it needs a durable queue and a
discussion, not a void promise.
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.
- 6d ago First seen · 89 lines · 77 tokens per session scan A bbc90516ecb4
audit-event is a skill published in the GitHub repository nacre-work/nacre (0 stars, last pushed 8d ago), licensed Apache-2.0. It adds 77 tokens to every session and 941 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
chroma
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source…
chroma
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source…
chroma
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source…
chroma
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source…
chroma
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source…
chroma
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source…