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 agentmods add skills/snowflake-labs/cocoplus/audit-exportnpx skills add Snowflake-Labs/cocoplus --skill audit-exportgit clone --depth 1 https://github.com/Snowflake-Labs/cocoplusWrote 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/snowflake-labs/cocoplus/audit-export)<a href="https://agentmods.dev/skills/snowflake-labs/cocoplus/audit-export"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/audit-export.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 | $0.00015 | $0.00385 |
| Opus 5 | $0.00008 | $0.00192 |
| Sonnet 5 | $0.00003 | $0.00077 |
| Haiku 4.5 | $0.00002 | $0.00038 |
Grade A, and why
audit-export 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 yesterday.
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.
What it actually says
$audit export
Export the complete CocoAudit trail as a uniquely timestamped compliance document. For stakeholder packaging, route Markdown/HTML/PDF formats through the shared exporter.
Steps
- Read
lifecycle/audit.md(append-only source of truth) - Count total event blocks (lines starting with
## [) - Generate timestamp:
YYYY-MM-DDTHH-MM-SSZ(hyphens replace colons for filesystem safety) - Write
.cocoplus/audit-export-[timestamp].mdwith header + full verbatim trail - If a format was requested, run
invoke reporting/report-export --source <exported-md> --format <markdown|html|pdf> --out-dir .cocoplus/audit-exports - Output path, event count, and export renderer status to developer
- Never overwrite prior export files — each invocation is uniquely timestamped (idempotent per export)
Exit Criteria
- Export file written to
.cocoplus/audit-export-[timestamp].md - Developer sees path and total event count
- No prior export file overwritten
- HTML export is available through
reporting/report-export; PDF reports renderer status if no renderer is configured
Anti-Rationalization
| Temptation | Why Wrong |
|---|---|
| Reuse same filename on same-day exports | Timestamp includes time — each export is unique and non-destructive |
| Read audit.md selectively | Source of truth is verbatim — export must include all events, not filtered view |
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.
- yesterday First seen · 39 lines · 15 tokens per session scan A 22f649271ff2
audit-export is a skill published in the GitHub repository Snowflake-Labs/cocoplus (720 stars, last pushed 2d ago), licensed MIT. It adds 15 tokens to every session and 385 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
meta-pdf-reformat-pipeline
Modernize a legacy PDF: structural extraction → natural-language rewrite of problem pages → audit summary → re-merge into the final PDF.
slides
Create and edit presentation decks as single self-contained HTML files with a live, editable preview and print-to-PDF export. Use when the user wants slides, a deck, or a presentation.
Read and extract text from .pdf files, page by page. Use when the user uploads or references a PDF to read or summarize.
human-summary
Write a human-readable mathematical progress report (compiled PDF) on a project for the operator / the mathematician who posed the problem. This is NOT elaboration (the internal strategy synthesis) and NOT the dashboard. Render from the fact graph's verified statements/proofs into a clean, self-contained report …
liteparse
Provides fast document to markdown extraction. Use this skill when the user asks to parse, perform multi-format document conversion or spatially extract text from an unstructured file (PDF, DOCX, PPTX, XLSX, images, etc.) locally.
anydoc
Convert Word (.doc/.docx/.docm), PowerPoint (.ppt/.pps/.pot/.pptx/.pptm/.ppsx/.ppsm), Excel (.xls/.xlsx/.xlsm/.xlsb), OpenDocument (.odt/.ods/.odp), RTF, EPUB, CSV, and PDF documents to clean GitHub-Flavored Markdown locally with the Any Doc CLI (npx -y @firecrawl/[email protected]): headings, GFM tables, slide structure…