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.
npx skills add Jeffallan/writing-with-agents --skill quality-rubricgit clone --depth 1 https://github.com/Jeffallan/writing-with-agentsWrote 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.
[](https://agentmods.dev/skills/jeffallan/writing-with-agents/quality-rubric)<a href="https://agentmods.dev/skills/jeffallan/writing-with-agents/quality-rubric"><img src="https://agentmods.dev/badge/skills/jeffallan/writing-with-agents/quality-rubric/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.
<a href="https://agentmods.dev/skills/jeffallan/writing-with-agents/quality-rubric"><img src="https://agentmods.dev/badge/skills/jeffallan/writing-with-agents/quality-rubric.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00036 | $0.02009 |
| Opus 5 | $0.00018 | $0.01005 |
| Sonnet 5 | $0.00007 | $0.00402 |
| Haiku 4.5 | $0.00004 | $0.00201 |
Grade A, and why
quality-rubric 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role Definition
The Quality Rubric is the evaluation specialist. AI scores finished content across 10 dimensions on a 1-5 scale and maps any dimension scoring below 4 back to the responsible workflow phase for targeted rework.
Lead: AI evaluates and scores each dimension with evidence-based justification. Support: Human reviews the scorecard, approves or overrides scores, and decides whether to accept rework recommendations.
A publishable piece scores 4 or higher on every critical dimension for its content type. The Quality Rubric does not perform rework itself. It identifies what needs fixing and routes the piece back to the correct phase. The responsible phase then executes the fix under its own workflow.
This skill sits downstream of the Judge phase. The Judge handles line-level detection and polish. The Quality Rubric steps back and evaluates the piece holistically across all dimensions that matter for publication.
When to Use This Skill
- After the Judge phase has completed all detection passes and the human has approved edits
- Before publishing, as a final gate to confirm the piece meets minimum standards
- When deciding whether a piece needs rework and which phase should handle it
- When comparing multiple drafts or revisions against a consistent scoring standard
- When a piece feels "off" but the specific weaknesses are hard to articulate
- When establishing quality baselines for a new content type or publication
- When a piece has gone through multiple rework cycles and you need objective evidence of improvement
- When onboarding a new publication standard and need to calibrate expectations with scored examples
- When prioritizing which of several finished drafts to publish first based on quality ranking
Core Workflow
- Receive polished draft from Judge phase -- Read the full draft, the original Architect blueprint, and any Judge detection reports. Confirm with the human that the Judge phase is complete and the piece is ready for quality evaluation. Do not score a draft that has not been through the Judge.
What ships with it
2 files 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.
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.
- 12d ago First seen · 131 lines · 36 tokens per session scan A 2a235df5d758
quality-rubric is a skill published in the GitHub repository Jeffallan/writing-with-agents (31 stars, last pushed 2mo ago), licensed MIT. It adds 36 tokens to every session and 2,009 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…