A read-only checker for a project's stored knowledge. It reviews recommendation groups, supporting evidence, wiki quality, outdated checks, ownership, and consistency.

It produces a health report for project-knowledge maintenance and highlights findings for human review.

It shows where project knowledge may be incomplete, stale, duplicated, or unreliable without changing the files.

pk-lint — Skill for Claude Code by szw321127

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.

Any agent

npx skills add szw321127/repowise --skill pk-lint

Clone the repo

git clone --depth 1 https://github.com/szw321127/repowise

Made for: Claude Code.

Or install pk, the plugin that ships this one along with the rest of its 9 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/szw321127/repowise/pk-lint/github.svg)](https://agentmods.dev/skills/szw321127/repowise/pk-lint)

Your own site

<a href="https://agentmods.dev/skills/szw321127/repowise/pk-lint"><img src="https://agentmods.dev/badge/skills/szw321127/repowise/pk-lint/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/szw321127/repowise/pk-lint"><img src="https://agentmods.dev/badge/skills/szw321127/repowise/pk-lint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 445 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.

Model	Per session	Once invoked
Fable 5.1	$0.00034	$0.00445
Opus 5	$0.00017	$0.00222
Sonnet 5	$0.00007	$0.00089
Haiku 4.5	$0.00003	$0.00044

Measured 10d ago against content hash 49cf6803091a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

pk-lint 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.

plugins/pk/skills/pk-lint/SKILL.md · 23 lines

What it actually says

PK Lint

Treat this skill as the read-only maintenance check for project knowledge.

Required Behavior

Accept either a project root or a .project-knowledge/ directory.
Resolve ../../scripts/pk-lint.mjs relative to this SKILL.md file.
The wrapper delegates to lint-project-knowledge.mjs.
Report the result in Chinese, including recommendation pools and any evidence, lifecycle, eviction, duplicate, wiki quality, stale verification, usefulness, ownership, or consistency issues.
Do not modify or delete project knowledge files.
Treat incubating-promotion-candidate, recommendation-pool-eviction-candidate, possible-duplicate-node, wiki-*, stale verification, and usefulness findings as human review prompts, not automatic promotion/deletion instructions.
Mention the wikiQuality, staleness, and usefulness summaries when they are present so the user can separate page-governance work from lifecycle-governance work and actual retrieval usefulness.
When wiki-evidence-record-missing-reason appears, explain that structured source_evidence records on stable nodes should include a short reason describing why the path proves the practice, option, or rule.
When node-missing-evidence-path appears, explain that the evidence path no longer exists in the project; include any repair_candidates as review hints, not automatic rewrites.
When wiki-never-hit, wiki-hit-but-never-adopted, or wiki-frequently-rejected-after-hit appears, explain that the node may need better keywords/applicability, lower ranking, narrower scope, or archival.
When wiki-active-conflicting-rules, wiki-superseded-node-still-recommended, or wiki-duplicate-practice-scope appears, explain that maintainers should resolve explicit conflicts, remove superseded nodes from recommendation surfaces, or merge/split overlapping practice scopes.

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.

10d ago First seen · 23 lines · 34 tokens per session scan A 49cf6803091a

Subscribe to this mod's changes

pk-lint is a skill published in the GitHub repository szw321127/repowise (21 stars, last pushed 3mo ago), licensed MIT. It adds 34 tokens to every session and 445 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.

Analytics and metrics

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