spiral-audit

spiral-audit is a command for Claude Code from Randroids-Dojo/skills. It costs 9 tokens per session (397 once invoked), scanned A, original, MIT.

A command that compares a repository with a standard Spiral project setup and prints a checklist of differences. Spiral is a scaffold for running structured, autonomous coding work.

In plain words
What is it for?
Run it on an existing repository to check readiness for an autonomous pull-request workflow, investigate drift after a long run, or assess a project that was not initialized with Spiral.
Why use it?
It reveals missing files, outdated tracking documents, weak progress coverage, and other setup gaps before they cause a project to appear finished too early.

Command for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the spiral plugin — 1 skill, 2 commands shipped together

Good fit Run it on an existing repository to check readiness for an autonomous pull-request workflow, investigate drift after a long run, or assess a project that was not initialized with Spiral.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add Randroids-Dojo/skills
Claude Code
/plugin install spiral

Made for: Claude Code.

Or install spiral, the plugin that ships this one along with the rest of its 1 skill, 2 commands.

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 spiral-audit

README.md
[![agentmods](https://agentmods.dev/badge/commands/randroids-dojo/skills/spiral-audit/github.svg)](https://agentmods.dev/commands/randroids-dojo/skills/spiral-audit)
Your own site
<a href="https://agentmods.dev/commands/randroids-dojo/skills/spiral-audit"><img src="https://agentmods.dev/badge/commands/randroids-dojo/skills/spiral-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.

agentmods 80×15 button for spiral-audit

Your own site · 80×15
<a href="https://agentmods.dev/commands/randroids-dojo/skills/spiral-audit"><img src="https://agentmods.dev/badge/commands/randroids-dojo/skills/spiral-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 397 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00009 $0.00397
Opus 5 $0.00005 $0.00198
Sonnet 5 $0.00002 $0.00079
Haiku 4.5 $0.00001 $0.00040

Measured 5d ago against content hash eb9c83f7cfe8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

spiral-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 5d 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.

plugins/spiral/commands/spiral-audit.md · 44 lines

What it actually says

/spiral audit

Diff the current repo against the canonical spiral scaffold and print a remediation checklist.

When to use

On any existing repo to check whether it is a fit substrate for an autonomous PR loop. Runs eight checks and reports drift. Does not modify anything.

Run this:

  • After randroid:loop completes a long run, to surface stale ledgers.
  • Before assuming a project is "done." Catches the Flatline failure mode (chapter-granular coverage + missing qualitative gate = early termination).
  • When inheriting a project that was set up without spiral init, to see how much retrofit is needed.

How to invoke

bash ${CLAUDE_PLUGIN_ROOT}/scripts/audit.sh [path-to-repo]

Default path is the current directory.

What it checks

  1. Missing canonical files (including docs/DEPENDENCY_LEDGER.md).
  2. Monolith docs/GDD.md instead of a docs/gdd/ tree.
  3. Chapter-granular coverage rows (heuristic: fewer than 14 rows per project-week).
  4. Missing qualitative gate (docs/PLAYTEST.md or docs/FUN_FACTOR_AUDIT.md).
  5. Stale progress log (newest entry older than 7 days).
  6. Open questions without Recommended default: lines.
  7. Followups without Priority: tags.
  8. Em-dash drift in the canonical files.
  9. docs/DEPENDENCY_LEDGER.md missing the ## Watch list section (the Dependency Upgrade Gate has nothing to fire against without it).

Output

A checklist with one line per finding, ordered from most-blocking to least-blocking. No remediation file is written. Fix in place, re-run.

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. 5d ago Changed · +6 lines · +9 tokens per session eb9c83f7cfe8
  2. 9d ago First seen · 38 lines · 0 tokens per session scan A d0ad0047ba2a

Subscribe to this mod's changes

spiral-audit is a command published in the GitHub repository Randroids-Dojo/skills (46 stars, last pushed 9d ago), licensed MIT. It adds 9 tokens to every session and 397 once invoked, about $0.0000 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 2026-08-30.