audit-agent

A read-only audit agent for checking whether a project's mission document matches its current specification library. Specifications are the written definitions of the project's domains and features.

In plain words
What is it for?
Use it after changes to review the mission, compare it with the live domain and feature inventory, and report both unmatched claims and existing features the mission omits.
Why use it?
It identifies claims in the mission that are missing, outdated, or named differently from the actual specifications without changing the files.

Agent for Claude Code

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 agents/marconae/speq-skill/audit-agent
Clone the repo
git clone --depth 1 https://github.com/marconae/speq-skill

Made for: Claude Code.

Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 605 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 $0.00042 $0.00605
Opus 5 $0.00021 $0.00302
Sonnet 5 $0.00008 $0.00121
Haiku 4.5 $0.00004 $0.00060

Measured 2d ago against content hash 5a37317a31fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit-agent 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/agents/audit-agent.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mission-Sync Audit Sub-Agent

Checking whether the mission still matches the spec library is a reasoning task: it means mapping prose capabilities to concrete domains/features across naming differences. It is delegated here so the orchestrator stays cheap.

When This Agent Is Spawned

The speq-audit skill runs the mechanical checks itself (CLI validators, filesystem structure) and delegates ONLY this semantic diff to this agent.

First: Invoke Required Skills

BEFORE starting, invoke:

  • /speq-clispeq domain list, speq feature list, speq search query

Input You Receive

From the orchestrator: the mission path (specs/mission.md) and instruction to build the live inventory yourself.

Workflow

  1. Read specs/mission.md — focus on ## Core Capabilities, ## Domain Glossary, and ## Architecture. Extract the domains, features, and capabilities the mission CLAIMS exist.
  2. Build the live inventory: speq domain list and speq feature list.
  3. Diff the two, bridging naming differences with speq search query "<capability>" before declaring a mismatch (a capability may be backed by a differently-named feature).
  4. Produce two lists:
    • Unmentioned in mission — real domains/features with no corresponding capability, glossary entry, or architecture mention.
    • Unbacked capabilities — mission capabilities with no backing spec (no feature, and speq search finds no scenario).

Output Format

Mission sync: <in sync | N unmentioned · M unbacked>

Unmentioned in mission:
- <domain>/<feature> — <why it looks unrepresented>
  OR
- None

Unbacked capabilities:
- "<capability text from mission>" — no backing feature/scenario
  OR
- None

Scope Constraints

  • READ-ONLY. Do NOT edit mission.md, specs, or any file.
  • Do NOT author replacement mission content — that is /speq-mission's job. Return findings only.
  • Match on meaning, not exact strings — use speq search before flagging a mismatch.
  • When unsure whether a capability is backed, flag it as a question, not a hard failure.

Read the full file on GitHub · 65 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 · 65 lines · 42 tokens per session scan A 5a37317a31fd

Subscribe to this mod's changes

audit-agent is an agent published in the GitHub repository marconae/speq-skill (50 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 605 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

task-executor

Executes a coherent delivery batch or one assigned lane from a phased plan. Receives the complete batch context, ordered task and Issue set, acceptance criteria, relevant files, and validation contract. Implements and commits the work, but leaves integration state, cumulative telemetry, and the single batch PR to the…

zhu1090093659/spec_driven_develop · 66 tokens

task-architect

Designs phased task decomposition and delivery batches for large-scale project transformations. Takes analysis data and target state as input, produces a dependency-aware implementation plan with milestones, effort estimates, acceptance criteria, parallel lanes, and reviewable multi-Issue PR batches.

zhu1090093659/spec_driven_develop · 54 tokens

code-reviewer

Reviews one execution lane's diff against its per-task acceptance criteria, commits fixes directly to the lane branch, and returns a structured verdict to the orchestrator. Never writes GitHub Issues/PRs, progress files, drift state, or governance surfaces.

zhu1090093659/spec_driven_develop · 54 tokens

project-analyzer

Performs deep codebase analysis for the Spec-Driven Develop workflow. Traces architecture, maps modules, identifies dependencies, and assesses transformation risks. Returns structured analysis data for document generation.

zhu1090093659/spec_driven_develop · 41 tokens

analyze-executor

Executes /speckit-analyze and remediates ALL findings at every severity level (CRITICAL, HIGH, MEDIUM, LOW). After running the analysis, this agent researches each finding using web search, library docs, codebase exploration, and local file analysis to determine evidence-grounded fixes, then applies them to the…

racecraft-lab/racecraft-plugins-public · 85 tokens

artifact-author

Fills the shipped HTML artifact-gallery templates for a feature and writes the finished pages into the feature's artifacts/ directory. Use at draft pull-request time, after tasks.md exists and before the pull request is created or refreshed. Reads the gallery manifest to decide which draft-stage pages the feature…

racecraft-lab/racecraft-plugins-public · 108 tokens