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 cpliakas/claude-code-engineering-leaders --skill refine-storygit clone --depth 1 https://github.com/cpliakas/claude-code-engineering-leadersWrote 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/cpliakas/claude-code-engineering-leaders/refine-story)<a href="https://agentmods.dev/skills/cpliakas/claude-code-engineering-leaders/refine-story"><img src="https://agentmods.dev/badge/skills/cpliakas/claude-code-engineering-leaders/refine-story/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/cpliakas/claude-code-engineering-leaders/refine-story"><img src="https://agentmods.dev/badge/skills/cpliakas/claude-code-engineering-leaders/refine-story.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 | $0.00037 | $0.03027 |
| Opus 5 | $0.00018 | $0.01514 |
| Sonnet 5 | $0.00007 | $0.00605 |
| Haiku 4.5 | $0.00004 | $0.00303 |
Grade A, and why
refine-story 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 10d 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 — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refine Story
Score a story draft against INVEST criteria and eight agile coaching principles. Returns a structured report with pass/fail per dimension and specific rewrites or corrective actions for every failure.
Input
$ARGUMENTS = the story draft to review (paste the full story text, or describe the story if no draft is available yet).
Process
1. Parse Input
Read the story draft. Identify:
- Title
- User Story statement (role, capability, benefit)
- Acceptance Criteria list
- Technical Notes section (if present)
- Definition of Done section (if present)
- Any scope statements
If only a description is provided (no draft), construct a minimal story from the description to give the scoring something to evaluate, and note that the review is based on a reconstructed draft.
2. Score INVEST
Score each of the six INVEST dimensions. For each, produce PASS or FAIL with a one-sentence explanation.
| Criterion | Question | Common failure |
|---|---|---|
| Independent | Can this be delivered without waiting on another in-progress story? | Coupled to another story's implementation |
| Negotiable | Does it describe the what/why and leave room for how? | Specifies UI layout, API shape, or implementation approach |
| Valuable | Does the benefit statement name a real outcome for the role? | "So that the code is cleaner" — that's a refactor, not a user story |
| Estimable | Is there enough detail to estimate effort? | Vague scope, unknown integration, missing constraints |
| Small | Can it be completed in a single sprint? | Epic-sized scope, more than 7-8 acceptance criteria |
| Testable | Can every acceptance criterion be verified with a concrete test? | "Works correctly", "Handles all edge cases" |
3. Evaluate Coaching Principles
Evaluate each of the eight principles with PASS or FAIL. For every FAIL, provide a specific issue and a suggested rewrite or corrective action.
Principle 1 — AC Outcome-Orientation
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.
- 10d ago First seen · 281 lines · 37 tokens per session scan A 32e7b61e3688
refine-story is a skill published in the GitHub repository cpliakas/claude-code-engineering-leaders (4 stars, last pushed 18d ago), licensed MIT. It adds 37 tokens to every session and 3,027 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.
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…