knowledge-mcp: Skill for Claude Code

.claude/skills/author-criteria/SKILL.md

author-criteria is a skill for Claude Code from fulminate-io/knowledge-mcp. It costs 52 tokens per session (3,731 once invoked), scanned A, original, Apache-2.0.

A rulebook for writing project criteria that define required behavior, performance, and effects on existing code.

In plain words
What is it for?
It is for authoring acceptance criteria and execution checks during software planning.
Why use it?
It helps prevent vague criteria that cannot prove whether a change works or breaks related code.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

This is fulminate-io/knowledge-mcp's own configuration. It tells Claude Code how to work on knowledge-mcp 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 knowledge-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to fulminate-io/knowledge-mcp. 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/fulminate-io/knowledge-mcp/main/.claude/skills/author-criteria/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/fulminate-io/knowledge-mcp

Made for: Claude Code.

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 author-criteria

README.md
[![agentmods](https://agentmods.dev/badge/skills/fulminate-io/knowledge-mcp/author-criteria/github.svg)](https://agentmods.dev/skills/fulminate-io/knowledge-mcp/author-criteria)
Your own site
<a href="https://agentmods.dev/skills/fulminate-io/knowledge-mcp/author-criteria"><img src="https://agentmods.dev/badge/skills/fulminate-io/knowledge-mcp/author-criteria/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.

agentmods 80×15 button for author-criteria

Your own site · 80×15
<a href="https://agentmods.dev/skills/fulminate-io/knowledge-mcp/author-criteria"><img src="https://agentmods.dev/badge/skills/fulminate-io/knowledge-mcp/author-criteria.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,731 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 $0.00052 $0.03731
Opus 5 $0.00026 $0.01865
Sonnet 5 $0.00010 $0.00746
Haiku 4.5 $0.00005 $0.00373

Measured 6d ago against content hash 2be633ff8a83, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

author-criteria 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 6d 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/skills/author-criteria/SKILL.md · 259 lines

How it starts

The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AUTHOR-CRITERIA — writing a criterion that can carry weight

WHAT CRITERIA ARE

Criteria are GUARDRAILS on how new additions or changes will work with and affect the ecosystem, and on how the changes solve the goal. Every criterion belongs to exactly one of THREE CATEGORIES, declared on the criterion:

  1. PERFORMANCE — the change meets its cost shape under real scale: the batch stays batched, the hot path stays allocation-flat, the query rides its index, the measured band holds at the scales the work will meet.
  2. LOGIC FAILURES — the finished work behaves as intended and the wrong-but-compiling implementation is rejected: given this input, that output; this invariant holds under that operation; the forbidden state cannot be reached; the semantics match the goal.
  3. BLAST RADIUS — the change's effect on existing OUT-OF-SCOPE code that depends on what changed: dependents still behave correctly (exercise their paths, run their suites against the change), contracts consumers rely on still hold, and nothing the change retired is still load-bearing somewhere the scope fence didn't look.

A candidate criterion that fits none of the three is not a criterion. A plan whose set leaves any category unexamined states why (a doc-only change has no performance category; a leaf addition may have no blast radius — say so, with the reasoning, rather than padding).

NEVER GREP-SATISFIABLE: a criterion satisfiable by a grep — by any inspection of text — is definitionally not testing any of the three categories, because text inspection observes what the code SAYS, never what it DOES. A criterion's command EXECUTES the behavior it guards: runs the system, the suite, the probe, the measurement. Text tools may appear inside a command only to post-process executed output (asserting on a runner's PASS line, extracting a measured number) — never as the thing that decides. RECONCILIATION with the prose-deliverable rule (invariant sentences): a mandated prose artifact whose subject no execution can observe (a shipped doc row, a locked comment phrase) may carry a text leg that can REJECT — but GREEN always requires the criterion's executing legs to pass. Reject-only text legs do not make a criterion grep-satisfiable; a criterion whose green is reachable by text inspection alone does. A text leg guarding a prose CLASS (not one pinned string) owes a bad fixture per axis it claims to discriminate — case, word order, interposed tokens — or the pattern is re-derived from the step's own enumerated sites and checked against every one before storing. A known-positive control proves the probe ran; it never proves the pattern's shape matches the class.

Read the full file on GitHub · 259 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. 6d ago First seen · 259 lines · 52 tokens per session scan A 2be633ff8a83

Subscribe to this mod's changes

author-criteria is a skill published in the GitHub repository fulminate-io/knowledge-mcp (1 stars, last pushed 5d ago), licensed Apache-2.0. It adds 52 tokens to every session and 3,731 once invoked, about $0.0003 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 2026-09-04.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 83 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens