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.
/plugin marketplace add cogni-work/insight-wave/plugin install cogni-knowledgeWrote 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/cogni-work/insight-wave/knowledge-lint)<a href="https://agentmods.dev/skills/cogni-work/insight-wave/knowledge-lint"><img src="https://agentmods.dev/badge/skills/cogni-work/insight-wave/knowledge-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.
<a href="https://agentmods.dev/skills/cogni-work/insight-wave/knowledge-lint"><img src="https://agentmods.dev/badge/skills/cogni-work/insight-wave/knowledge-lint.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 | $0.00118 | $0.02511 |
| Opus 5.5 | $0.00047 | $0.01004 |
| Sonnet 5.5 | $0.00024 | $0.00502 |
| Haiku 4.5 | $0.00012 | $0.00251 |
Grade A, and why
knowledge-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 1mo 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Lint
Run the semantic lint pass on a cogni-knowledge base — surface stale pages, stale drafts, claim drift, missing reverse links, entries-count drift, and formatting findings, and optionally repair the mechanical classes with --fix. This is the standalone analog of cogni-wiki:wiki-lint, computed natively on the vendored lint_wiki.py engine (resolved vendored-first via resolve_wiki_scripts()), so a Karpathy base is lintable with no cogni-wiki plugin installed.
Lint is read-only by default (a pure audit). It writes to the wiki only when the user passes --fix — and even then only the mechanical, deterministic repair classes the engine owns. This is the tokenful semantic counterpart to knowledge-health's cheap structural gate: run health first, reach for lint when you want to inspect or repair drift.
Read ${CLAUDE_PLUGIN_ROOT}/references/delegation-contract.md once at the start of a session so you remember the wiki-engine boundary — cogni-knowledge runs the lint pass on the vendored wiki-lint engine, it does not dispatch cogni-wiki:wiki-lint.
When to run
- User asks to lint, audit hygiene, or find/fix stale content in a knowledge base
- After noticing entries-count or claim drift in
knowledge-healthand wanting to reconcile it - Periodically as a maintenance pass on a compounding base
- Before a
knowledge-finalizerun, to clean reverse links and drift the synthesis would otherwise inherit
Never run when
- The target directory has no
.cogni-knowledge/binding.json— offerknowledge-setupinstead.
How it relates to neighbours
knowledge-healthis the cheap structural integrity gate (vendoredhealth.py);knowledge-lintis the semantic hygiene pass (vendoredlint_wiki.py). They share the bound base but answer different questions — run health for "is it broken?", lint for "is it stale / can it be tidied?".knowledge-finalizealready runslint --fix=allas its deposit-time conformance gate. This skill exposes the full lint CLI for deliberate, operator-driven runs (audit,--suggest, selective--fix=<class>).
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.
- 1mo ago Changed · -13 lines f8b62f79b584
- 1mo ago First seen · 150 lines · 118 tokens per session scan A 78badcfb837b
knowledge-lint is a skill published in the GitHub repository cogni-work/insight-wave (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 118 tokens to every session and 2,511 once invoked, about $0.0005 per session on Opus 5.5. 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
mem0-status
Diagnoses mem0 connectivity, API key validity, and memory read/write functionality. Use when memory operations fail, searches return empty, addmemory errors occur, or to verify the plugin is working correctly.
inspector-workbench
Runs Inspector UI work on the standalone Threads state lab so the agent can see the overlay. Use when a CopilotKit employee asks an agent to fix, polish, add, or debug Inspector UI, chrome, panes, overlay actions, launcher, Home, Threads, Playground, Memory, or any visual behavior in @copilotkit/web-inspector. Don't…
md-audit
Read-only code quality audit — scan the current working directory for common issues (bugs, dead code, security hotspots, missing error handling) and return a prioritised findings report. No files are edited. Use when asked to "audit the code", "quick audit", "find issues", "code scan", or "what's wrong with this…
potpie-debug-memory
Use while debugging or troubleshooting failures, flaky tests, incidents, production alerts, CI failures, local dev setup issues, repeated bugs, prior fixes, failed attempts, and verification history.
browserwing-admin
Manage and operate BrowserWing — an intelligent browser automation platform. Install dependencies, configure LLM, create/manage/execute automation scripts, use AI-driven exploration to generate scripts, browse the script marketplace, and troubleshoot issues.
code-understand
Map the load-bearing files, symbols, callers, and dependencies of an unfamiliar codebase before making changes. Use for architecture orientation, impact analysis, what-would-break questions, or finding callers. Uses CodeGraph when available and a dependency-free builtin fallback.