draft-audit-harness

draft-audit-harness is a skill for Claude Code, Codex from Stahl-G/briefloop. It costs 35 tokens per session (279 once invoked), scanned A, original, MIT.

A review guide for the draft audit stage, where a briefing is checked against its sources and citations. It covers unsupported claims, numbers, dates, placeholders, confidence wording, and leftover process notes.

In plain words
What is it for?
Use it when changing audit logic or tests for citation coverage, source support, orphan claim IDs, stale wording, unsupported numbers, and low-confidence claims.
Why use it?
It catches statements that cannot be supported or that may mislead readers before a briefing is delivered. It also turns findings into concrete rules and regression tests.

Skill for Claude CodeCodex

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/stahl-g/briefloop/draft-audit-harness
Any agent
npx skills add Stahl-G/briefloop --skill draft-audit-harness
Clone the repo
git clone --depth 1 https://github.com/Stahl-G/briefloop

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.

agentmods badge for draft-audit-harness

README.md
[![agentmods](https://agentmods.dev/badge/skills/stahl-g/briefloop/draft-audit-harness.svg)](https://agentmods.dev/skills/stahl-g/briefloop/draft-audit-harness)
Your own site
<a href="https://agentmods.dev/skills/stahl-g/briefloop/draft-audit-harness"><img src="https://agentmods.dev/badge/skills/stahl-g/briefloop/draft-audit-harness.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 279 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 $0.00035 $0.00279
Opus 5 $0.00017 $0.00139
Sonnet 5 $0.00007 $0.00056
Haiku 4.5 $0.00003 $0.00028

Measured 5d ago against content hash e4f7736812a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

draft-audit-harness 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.

.agents/skills/draft-audit-harness/SKILL.md · 42 lines

What it actually says

Draft Audit Harness Skill Contract

Scope

This is a runtime skill contract. It describes the capability and artifact contract for this role.

It is not the platform-specific subagent definition. Claude Code subagents live in .claude/agents/; OpenCode subagents live in .opencode/agents/; Codex custom agents live in .codex/agents/; Hermes child tasks are created through delegate_task.

Purpose

Review and implement draft-level audit harness behavior.

Use When

Use when changing audit logic for citations, source support, numbers, source dates, placeholders, confidence leakage, or process residue.

Inputs

  • output/intermediate/audited_brief.md
  • output/intermediate/claim_ledger.json
  • audit rule code or tests

Outputs

  • audit findings
  • updated audit rules or tests when requested

Work

  • Check citation coverage, orphan claim IDs, unsupported numbers, stale wording, and low-confidence leakage.
  • Map each finding to a concrete rule or test.
  • Keep deterministic gates in code and regression tests rather than prompt text.

Handoff

Return rule/test changes and remaining audit risks.

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 First seen · 42 lines · 35 tokens per session scan A e4f7736812a9

Subscribe to this mod's changes

draft-audit-harness is a skill published in the GitHub repository Stahl-G/briefloop (9 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 279 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 2026-08-31.

Related

Other skills, from other repositories

ibrahim-daily-briefing

Generate Ibrahim's daily briefing — new leads, upcoming calls, pending follow-ups, system health, and one strategic question. Delivered to Telegram.

S3YED/appie-kit · 37 tokens

tax-lawyer-evidence-graph

Evidence graph construction for tax audit trails. Each Satisfies check emits EvidenceNode structs with Blake3 content hashes. Evidence chains are tamper-evident and link legislative citations to factual findings.

elasticdotventures/_b00t_ · 49 tokens

edgeone skill scanner

Scan any agent skill for security risks before you install or use it. Powered by Tencent Zhuque Lab A.I.G (AI-Infra-Guard). 100% local static analysis — no file contents or credentials leave your device. Compatible with CodeBuddy, Cursor, Windsurf, Claude Code, OpenClaw and more. Triggers on: 这个 skill 安全吗, skill 安全扫描…

Tencent/AI-Infra-Guard · 148 tokens

top-design

Create award-winning, immersive web experiences at the level of Awwwards-featured agencies. Use when the user mentions "Awwwards quality", "make my site stunning", "scroll animations", "parallax storytelling", "cinematic web design", "portfolio site", or "brand experience". Also trigger when elevating a standard…

wondelai/skills · 113 tokens

traction-eos

Implement the Entrepreneurial Operating System (EOS) to align vision and execution across a company. Use when the user mentions "EOS", "Entrepreneurial Operating System", "V/TO", "quarterly rocks", "Level 10 meetings", "accountability chart", "IDS process", "my company feels chaotic", "we keep having the same…

wondelai/skills · 147 tokens

agent-review

Critically review a Stencila agent and suggest improvements. Use when asked to review, audit, critique, evaluate, or improve an agent directory or AGENT.md file. Covers frontmatter validation, system instruction quality, configuration correctness, and adherence to the Agent schema.

stencila/stencila · 57 tokens