briefloop: Skill for Claude Code

.agents/skills/final-quality-harness/SKILL.md

final-quality-harness is a skill for Claude Code, Codex from Stahl-G/briefloop. It costs 28 tokens per session (285 once invoked), scanned A, original, MIT.

A review skill for checking whether reader-facing text and delivery files are ready to publish after factual review. It also covers the rules and tests used for these final checks.

In plain words
What is it for?
It is for reviewing briefs and optional DOCX files, identifying publication blockers, and maintaining regression tests for final-quality rules.
Why use it?
It catches presentation and delivery problems that a fact-check alone may miss, such as stale framing, weak summaries, or leftover internal notes.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

This is Stahl-G/briefloop's own configuration. It tells Claude Code and Codex how to work on briefloop itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything briefloop configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Stahl-G/briefloop. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Stahl-G/briefloop/main/.agents/skills/final-quality-harness/SKILL.md
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 final-quality-harness

README.md
[![agentmods](https://agentmods.dev/badge/skills/stahl-g/briefloop/final-quality-harness.svg)](https://agentmods.dev/skills/stahl-g/briefloop/final-quality-harness)
Your own site
<a href="https://agentmods.dev/skills/stahl-g/briefloop/final-quality-harness"><img src="https://agentmods.dev/badge/skills/stahl-g/briefloop/final-quality-harness.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 285 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 $0.00028 $0.00285
Opus 5 $0.00014 $0.00143
Sonnet 5 $0.00006 $0.00057
Haiku 4.5 $0.00003 $0.00028

Measured 7d ago against content hash ca68ae614e51, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

final-quality-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 7d 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/final-quality-harness/SKILL.md · 43 lines

What it actually says

Final Quality 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 final text delivery gates for publication readiness.

Use When

Use when changing final report depth, quiet-week handling, front-page metadata, stale-current framing, executive summary quality, or internal residue checks.

Inputs

  • output/delivery/brief.md
  • output/delivery/<named>.docx when DOCX delivery is configured
  • output/intermediate/audit_report.json
  • final quality rule code or tests

Outputs

  • final quality findings
  • updated final quality rules or tests when requested

Work

  • Check whether reader-facing output is publication-ready after factual audit.
  • Identify delivery blockers that are not source-support problems.
  • Keep final quality checks as harness rules and regression tests.

Handoff

Return delivery readiness status and any blocking final-quality issues.

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. 7d ago First seen · 43 lines · 28 tokens per session scan A ca68ae614e51

Subscribe to this mod's changes

final-quality-harness is a skill published in the GitHub repository Stahl-G/briefloop (9 stars, last pushed 3d ago), licensed MIT. It adds 28 tokens to every session and 285 once invoked, about $0.0001 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

geo-proposal

Auto-generate a professional, client-ready GEO service proposal from audit data. Creates a full proposal in markdown and PDF including executive summary, findings, recommended service packages (Basic/Standard/Premium), pricing, timeline, and terms. Use when user says "proposal", "proposta", "offerta", "preventivo"…

zubair-trabzada/geo-seo-claude · 83 tokens

document-generation

Generate Word (.docx), Excel (.xlsx) and PowerPoint (.pptx) documents and fill existing PDF forms, from real NetClaw data, with per-element provenance and no fabrication. Use when someone needs a deliverable rather than an answer — a change record to attach to a CR, an audit workbook for a compliance reviewer, a…

automateyournetwork/netclaw · 91 tokens

network-report-documents

The four standard NetClaw document compositions — a change-record Word document from a real ServiceNow CR plus device state, an interface/config audit workbook from real device queries, an executive summary deck with an embedded topology diagram, and a required PDF form filled from real data. Use when an operator asks…

automateyournetwork/netclaw · 88 tokens

audit-export

Export the full CocoAudit trail as a stakeholder-ready compliance document.

Snowflake-Labs/cocoplus · 15 tokens

geo-proposal

Auto-generate a professional, client-ready GEO service proposal from audit data. Creates a full proposal in markdown and PDF including executive summary, findings, recommended service packages (Basic/Standard/Premium), pricing, timeline, and terms. Use when user says "proposal", "proposta", "offerta", "preventivo"…

asale-ai/seo-geo-skill · 83 tokens

wuji-document-suite

Unified office-document Skill for Word, PDF, and spreadsheet creation, editing, rendering, redlining, and verification. Use whenever the primary deliverable is DOCX, PDF, XLSX, CSV, or a related office artifact.

AI-wuji/wuji-legion-codex · 51 tokens