A reader and checker for a tamper-evident audit log, which is a record designed to reveal changes or missing entries. It can show events, verify the record, and rebuild sprint status.

Use it to filter activity by sprint, skill, or time, verify the log’s hash chain, or replay a sprint’s recorded state.

It helps people see what the coding agent did and detect whether the action history was altered or corrupted.

audit — Skill for Claude Code and Codex by rijuvashisht

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.

Any agent

npx skills add rijuvashisht/Magneto --skill audit

Clone the repo

git clone --depth 1 https://github.com/rijuvashisht/Magneto

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/rijuvashisht/magneto/audit/github.svg)](https://agentmods.dev/skills/rijuvashisht/magneto/audit)

Your own site

<a href="https://agentmods.dev/skills/rijuvashisht/magneto/audit"><img src="https://agentmods.dev/badge/skills/rijuvashisht/magneto/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/rijuvashisht/magneto/audit"><img src="https://agentmods.dev/badge/skills/rijuvashisht/magneto/audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 655 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.00655
Opus 5	$0.00000	$0.00328
Sonnet 5	$0.00000	$0.00131
Haiku 4.5	$0.00000	$0.00065

Measured 10d ago against content hash 5f6dc4d0e750, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

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 10d 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.

src/templates/magneto-skills/skills/audit/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/audit — Read the Tamper-Evident Audit Log

Role: Audit Log Reader Inputs: filters (sprint, skill, time range) Outputs: human-readable log or JSON Audit actions: audit.read, audit.verified

Why This Skill Exists — The Moat

Every Magneto skill invocation emits hash-chained events to .magneto/audit.jsonl. /audit lets humans read the log, verify its integrity, and replay sprint state.

Enterprise feature: every AI action is traceable, reversible, governable.

Subcommands

Tail

magneto audit tail                    # last 20 events
magneto audit tail --sprint <id>      # filter by sprint
magneto audit tail --skill review     # filter by skill
magneto audit tail --since 1h         # time filter
magneto audit tail --follow           # live stream

Verify hash chain

magneto audit verify

Walks the chain and confirms:

Each event's prevHash matches the previous event's hash
Each event's hash is reproducible from its fields
No gaps in seq numbers

Exit code 0 = intact. Non-zero = tampered or corrupted.

Replay sprint state

magneto audit replay --sprint <id>

Reconstructs the sprint state by walking events:

Sprint started at <ts> by <actor>
/think drafted design with approach A
/plan drafted plan; 5 files modify, 2 create
/plan-eng-review scored: arch=8, tests=6
/review found 2 block, 3 ask findings
/ship opened PR #42
...

Search

magneto audit search --action "*.fail*"
magneto audit search --actor [email protected] --since 7d
magneto audit search --payload 'req=REQ-042'

Event Format

{
  "seq": 42,
  "ts": "2026-05-12T18:34:52.123Z",
  "actor": "[email protected]",
  "skill": "review",
  "action": "review.findings_recorded",
  "sprintId": "s-20260512-1800",
  "payload": { "block": 2, "autoFixed": 3, "ask": 1, "note": 5 },
  "prevHash": "abc123...",
  "hash": "def456..."
}

Compliance Export

magneto audit export --format json --since 30d > audit-export.json
magneto audit export --format csv --sprint s-... > sprint-audit.csv

Read the full file on GitHub · 90 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.

10d ago First seen · 90 lines · 0 tokens per session scan A 5f6dc4d0e750

Subscribe to this mod's changes

audit is a skill published in the GitHub repository rijuvashisht/Magneto (6 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 655 tokens. 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.

Security openai

skill-creator

Create, install, or update skills in the workspace. Use when (1) installing a skill from a URL or remote source, (2) creating a new skill from scratch, (3) updating or restructuring existing skills. Always use this skill for any skill installation or creation task.

zhayujie/CowAgent · 61 tokens

image-generation

Generate or edit images from text prompts. Use when the user asks to create, draw, design, or edit an image, illustration, photo, icon, poster, or any visual content.

zhayujie/CowAgent · 41 tokens

baby-sit

Monitor a GitHub pull request until CI is green, diagnose failures, and rerun only evidence-backed flaky GitHub Actions jobs.

langchain-ai/open-swe · 30 tokens

continual-learning

Nightly refinement of an existing per-repo review-style prompt using this reviewer's own finding outcomes. Read confirmed (resolved-by-commit / thumbs-up) and dismissed (thumbs-down) findings, promote the bug patterns the team actually fixes, demote the false-positive patterns, reconcile against the current prompt…

langchain-ai/open-swe · 89 tokens

peekaboo

Capture and automate macOS UI with the Peekaboo CLI.

the-open-agent/openagent · 17 tokens

powerpoint

Create designed, editable PowerPoint .pptx presentations with PptxGenJS. Use when the user asks to create, generate, update, or inspect a deck, slide deck, presentation, or .pptx file.

the-open-agent/openagent · 48 tokens