knowledge-health

knowledge-health is a skill for Claude Code from cogni-work/insight-wave. It costs 89 tokens per session (2,624 once invoked), scanned A, original, Apache-2.0.

A read-only checker for the structure of a research wiki, including its pages, links, required fields, entry counts, and claim changes.

In plain words
What is it for?
Use it to audit a knowledge base, especially after importing many sources or publishing a new synthesis, without changing any files.
Why use it?
It shows whether the knowledge base is structurally sound and flags drift after large updates.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the cogni-knowledge plugin — 23 skills, 16 agents shipped together

Good fit Use it to audit a knowledge base, especially after importing many sources or publishing a new synthesis, without changing any files.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add cogni-work/insight-wave
Claude Code
/plugin install cogni-knowledge

Made for: Claude Code.

Or install cogni-knowledge, the plugin that ships this one along with the rest of its 23 skills, 16 agents.

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 knowledge-health

README.md
[![agentmods](https://agentmods.dev/badge/skills/cogni-work/insight-wave/knowledge-health/github.svg)](https://agentmods.dev/skills/cogni-work/insight-wave/knowledge-health)
Your own site
<a href="https://agentmods.dev/skills/cogni-work/insight-wave/knowledge-health"><img src="https://agentmods.dev/badge/skills/cogni-work/insight-wave/knowledge-health/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 knowledge-health

Your own site · 80×15
<a href="https://agentmods.dev/skills/cogni-work/insight-wave/knowledge-health"><img src="https://agentmods.dev/badge/skills/cogni-work/insight-wave/knowledge-health.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,624 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 $0.00089 $0.02624
Opus 5 $0.00044 $0.01312
Sonnet 5 $0.00018 $0.00525
Haiku 4.5 $0.00009 $0.00262

Measured 4d ago against content hash fb8eef74fddb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

knowledge-health 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 4d 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.

cogni-knowledge/skills/knowledge-health/SKILL.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Knowledge Health

Give the user a fast, grounded structural health verdict for a cogni-knowledge base — the page/link/schema integrity of the bound wiki, plus entries-count drift and claim drift. This is the standalone analog of cogni-wiki:wiki-health, computed natively on the vendored health.py engine (resolved vendored-first via resolve_wiki_scripts()), so a Karpathy base is health-checkable with no cogni-wiki plugin installed.

This skill is fully read-onlyhealth.py writes nothing (it emits JSON to stdout only). The health-check log line the retired cogni-wiki:wiki-health dispatch used to append was a workflow step of that skill, not of the engine; the native path has no append step.

Read ${CLAUDE_PLUGIN_ROOT}/references/delegation-contract.md once at the start of a session so you remember the wiki-engine boundary — cogni-knowledge computes the health verdict on the vendored wiki-health engine, it does not dispatch cogni-wiki:wiki-health.

When to run

  • User asks for a health check, integrity check, or structural verdict on a knowledge base
  • Right after a bulk knowledge-ingest or a knowledge-finalize run, to confirm the base is still structurally sound
  • Before sharing or publishing a base, as a pre-flight gate
  • Proactively when a session opens in a directory containing .cogni-knowledge/binding.json and the user asks "is everything OK?"

Never run when

  • The target directory has no .cogni-knowledge/binding.json — offer knowledge-setup instead.

How it relates to neighbours

  • knowledge-resume runs the same health.py engine for its one-line verdict but layers a full status overlay (deposited projects, next action). Use knowledge-health when you want the structural detail only, without the binding overlay.
  • knowledge-lint is the semantic pass (stale pages, claim drift, reverse-link repair with --fix). knowledge-health is the cheap structural gate; knowledge-lint is the tokenful curation pass. Run health first; reach for lint when health flags drift you want to fix.

Read the full file on GitHub · 138 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. 4d ago Changed · -13 lines fb8eef74fddb
  2. 9d ago First seen · 151 lines · 89 tokens per session scan A 522bbba7d4d4

Subscribe to this mod's changes

knowledge-health is a skill published in the GitHub repository cogni-work/insight-wave (13 stars, last pushed yesterday), licensed Apache-2.0. It adds 89 tokens to every session and 2,624 once invoked, about $0.0004 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.

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

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

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens