A read-only checker for projects that manage software behavior in specification files. It examines the specification library, decision logs, plans, mission alignment, and ignored files.

Use it to audit, health-check, lint, or sanity-check a speq project, including after cloning or inheriting one.

It finds structural or synchronization problems before they make project documentation unreliable, and can guide fixes after asking for approval.

speq-audit — Skill for Claude Code by marconae

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 marconae/speq-skill --skill speq-audit

Clone the repo

git clone --depth 1 https://github.com/marconae/speq-skill

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/marconae/speq-skill/speq-audit.svg)](https://agentmods.dev/skills/marconae/speq-skill/speq-audit)

Your own site

<a href="https://agentmods.dev/skills/marconae/speq-skill/speq-audit"><img src="https://agentmods.dev/badge/skills/marconae/speq-skill/speq-audit.svg" alt="Measured on agentmods" height="20"></a>

Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,780 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. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Excessive Agency · line 4
Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.

How audits are shown

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	$0.00077	$0.01780
Opus 5	$0.00039	$0.00890
Sonnet 5	$0.00015	$0.00356
Haiku 4.5	$0.00008	$0.00178

Measured 2d ago against content hash c4bc903891f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

speq-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 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.

.claude/skills/speq-audit/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec Auditor (Orchestrator)

Thin orchestrator. It runs read-only health checks over a speq project, delegates the mission ↔ spec-library sync check to audit-agent, prints a BLUF summary, and offers to fix each finding. Always ask before a fix.

Required Skills (for the orchestrator)

Invoke before starting:

/speq-cli — spec discovery and the validate commands
/speq-writing-guardrails — prose style for the summary

The audit-agent sub-agent invokes /speq-cli itself. Read references/checks.md for the per-check detection recipes, thresholds, and remediation procedures.

Workflow

Phase 0: Load Project Hook (orchestrator)

Check for .speq/audit-hook.md in the repo root.

Present: read it. Announce "Loaded project hook: .speq/audit-hook.md". Its content is authoritative: it can add to, change, or override any part of this workflow. If the hook conflicts with this workflow, the hook wins.
Absent: continue normally, no mention.

Note it (not its full content) as a Project Hook: line in the audit-agent brief below.

Phase 1: Preconditions (orchestrator)

Check: specs/ directory exists?
├─ Yes → proceed
└─ No  → STOP: "No spec library found. Run /speq-mission to bootstrap."

Phase 2: Run checks (orchestrator, READ-ONLY)

Run every check in references/checks.md, recording a ✓ / ✗ / ⚠ and a one-line detail for each. Modify nothing in this phase. The checks:

Spec structure — every spec.md is at specs/<domain>/<feature>/spec.md
Feature specs — speq feature validate
Decision log — old specs/decision-log.md vs new specs/_decision/; speq decision-log validate
_recorded gitignored — specs/.gitignore contains /_recorded
Mission sync — delegated to audit-agent (Phase 3)
Unrecorded plans — specs/_plans/*/ with a verification-report.md
Recorded-folder naming — _recorded/* follows NNN-<plan>
Library thresholds — >10 scenarios/spec, >8 features/domain
Reserved-dir gitignore — _decision/_plans tracked; only _recorded ignored
Git hygiene — git status --short specs/ is clean
Active-plan validity — speq plan validate <plan> per active plan
Project hooks — informational only; list any .speq/*-hook.md present

Read the full file on GitHub · 143 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

references/checks.md 7.4 KB

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.

2d ago Changed c4bc903891f9
8d ago First seen · 143 lines · 77 tokens per session scan A 471f46506f87

Subscribe to this mod's changes

speq-audit is a skill published in the GitHub repository marconae/speq-skill (50 stars, last pushed 2d ago), licensed MIT. It adds 77 tokens to every session and 1,780 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 2026-08-30.

Claude Code Debugging ai-agents artificial-intelligence coding-agent skills spec-driven-development

bug-investigator

Use when encountering any bug, test failure, or unexpected behavior during spec-superflow execution, before proposing fixes. Invoked automatically when build-executor hits a blockage.

MageByte-Zero/spec-superflow · 37 tokens

backprop

Bug → spec protocol. When a bug is found or a test fails, trace the cause, decide whether a new §V invariant would catch recurrence, append to §B. This is the one non-obvious thing SDD does that plan-then-execute doesn't. Triggers on test failure, bug report, post-mortem, or explicit user ask.

JuliusBrussee/cavekit · 76 tokens

check

Read-only drift detector. Diffs SPEC.md against current code and reports violations grouped by severity. Writes nothing — suggests remedies via the spec or build skills but never invokes them. Triggers when the user asks to check drift, audit the spec, verify invariants, or ask whether code still matches the spec.…

JuliusBrussee/cavekit · 102 tokens

speq-audit