cocoaudit

cocoaudit is a skill for Claude Code from Snowflake-Labs/cocoplus. It costs 16 tokens per session (1,540 once invoked), scanned A, original, MIT.

An append-only record of project-session actions and approvals, including plan gates, specifications, shipping confirmations, and review acknowledgments. Append-only means entries are added but not rewritten or deleted.

In plain words
What is it for?
Use it to review or export the project's audit trail and retain evidence of decisions and approvals.
Why use it?
It preserves an exact history for projects that need traceability, including regulated work.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Install

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.

agentmods
npx agentmods add skills/snowflake-labs/cocoplus/cocoaudit
Any agent
npx skills add Snowflake-Labs/cocoplus --skill cocoaudit
Clone the repo
git clone --depth 1 https://github.com/Snowflake-Labs/cocoplus

Made for: Claude Code.

Wrote 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.

agentmods badge for cocoaudit

README.md
[![agentmods](https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/cocoaudit.svg)](https://agentmods.dev/skills/snowflake-labs/cocoplus/cocoaudit)
Your own site
<a href="https://agentmods.dev/skills/snowflake-labs/cocoplus/cocoaudit"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/cocoaudit.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,540 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00016 $0.01540
Opus 5 $0.00008 $0.00770
Sonnet 5 $0.00003 $0.00308
Haiku 4.5 $0.00002 $0.00154

Measured 2d ago against content hash 0876b6e98293, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

cocoaudit 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 2d 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.

.cortex/skills/cocoaudit/cocoaudit.skill.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CocoAudit — Session Audit Trail

Overview

CocoAudit reads the append-only audit trail at lifecycle/audit.md. Every plan approval, spec gate passage, $ship confirmation, SecondEye acknowledgment, and CocoSentinel approval is recorded verbatim with an ISO 8601 UTC timestamp. The record is never summarized, never overwritten, and never deleted within a project's lifetime.

Enabling CocoAudit: Enabled at $pod init when the developer selects "Enable session audit trail? (recommended for regulated environments)". This creates modes/cocoaudit.on and initializes lifecycle/audit.md with a project header.

CocoContract Lifecycle Events (Feature 44 Enhancement)

CocoAudit records four categories of CocoContract event, written by contract-prove and the archive step of contract.skill.md via the same lifecycle/audit.md append logic the PostToolUse hook already uses:

  1. Contract declaration — full text of a new outcome contract (persona, observable result, falsifiability condition) plus the session ID and timestamp of declaration.
  2. Evidence submission — evidence tier (e2e / reference / spec / differential / unit), the function version hash at submission time, the result (pass/fail), and the verbatim evidence description.
  3. Stale-evidence detection — recorded when a previously passing evidence check is found stale due to a function version change: the prior passing version hash, the current version hash, and the detection timestamp.
  4. Contract archive — recorded when a contract is committed to outcomes/, with the contract content hash.

$audit ci

Extends $audit with a contract regression phase that runs before standard audit log verification. Invoke audit-ci. The regression phase reads all archived contracts in outcomes/, re-executes each contract's falsifiability condition where machine-executable (e2e checks against a real Cortex endpoint), and records pass/fail. A contract whose re-execution fails is a behavioral regression — reported with the same severity as a failing safety gate. Intended for use as a CI/CD pre-deployment gate.

Read the full file on GitHub · 127 lines

Changes

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.

  1. 2d ago First seen · 127 lines · 16 tokens per session scan A 0876b6e98293

Subscribe to this mod's changes

cocoaudit is a skill published in the GitHub repository Snowflake-Labs/cocoplus (720 stars, last pushed 3d ago), licensed MIT. It adds 16 tokens to every session and 1,540 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.

Related

Other skills, from other repositories

accessibility-compliance-audit

Comprehensive web accessibility (a11y) audit and compliance skill. Audits HTML, React, Vue, and Angular codebases against WCAG 2.2 AA standards. Activates when users ask for "accessibility audit", "a11y check", "WCAG compliance", "ADA compliance", "screen reader testing", "keyboard navigation audit", "color contrast…

JPeetz/agent-skills · 134 tokens

GRC & Compliance

Governance, risk, and compliance — risk assessment and scoring, control mapping across NIST CSF 2.0 / ISO 27001:2022 / SOC 2 / CIS Controls v8, gap analysis, audit evidence preparation, and security policy generation.

Masriyan/Claude-Code-CyberSecurity-Skill · 58 tokens

legal-strategy

Analyze legal and regulatory risk, IP, contracts, privacy, governance, and employment questions as structured issue-spotting for counsel. Do not use this methodology as legal advice or for technical security implementation, CRM, or delivery execution.

magnus919/agent-skills · 50 tokens

lawyer-expert

Expert-level legal systems, contracts, compliance, and legal technology. Use when the user mentions legal, contracts, compliance, law, or legal tech, or when the task involves Legal Systems, Legal Technology, Compliance Frameworks, or Contract Management.

personamanagmentlayer/pcl · 54 tokens

category-designer

Define a new category where your product wins by default. Reframe the buying decision. Triggers on: "create a category", "category design", "define my category", "category of one", "reframe the market", "position as category king", "new category", "category creation", "own a category", "category strategy"…

Affitor/affiliate-skills · 103 tokens

funnel-planner

Plan a complete affiliate funnel from research to revenue. Triggers on: "plan my affiliate funnel", "create a funnel strategy", "affiliate business plan", "how to start affiliate marketing", "full funnel roadmap", "plan from scratch", "week by week affiliate plan", "chain skills together", "build my funnel"…

Affitor/affiliate-skills · 87 tokens