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 knowns-dev/knowns --skill kn-docgit clone --depth 1 https://github.com/knowns-dev/knownsWrote 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/knowns-dev/knowns/kn-doc)<a href="https://agentmods.dev/skills/knowns-dev/knowns/kn-doc"><img src="https://agentmods.dev/badge/skills/knowns-dev/knowns/kn-doc/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/knowns-dev/knowns/kn-doc"><img src="https://agentmods.dev/badge/skills/knowns-dev/knowns/kn-doc.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00020 | $0.01098 |
| Opus 5.5 | $0.00008 | $0.00439 |
| Sonnet 5.5 | $0.00004 | $0.00220 |
| Haiku 4.5 | $0.00002 | $0.00110 |
Grade A, and why
kn-doc 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working with Documentation
Announce: "Using kn-doc to work with documentation."
Core principle: SEARCH BEFORE CREATING - avoid duplicates.
Inputs
- Doc path, topic, folder, or task/spec reference
- Whether this is a create, update, or search request
Preflight
- Search before creating
- Prefer section edits for targeted changes
- Preserve doc structure and metadata unless the user asked for a restructure
- Validate refs after doc changes
Quick Reference
// List docs
mcp_knowns_docs({ "action": "list" })
// View doc (smart mode)
mcp_knowns_docs({ "action": "get", "path": "<path>", "smart": true })
// Search docs
mcp_knowns_search({ "action": "search", "query": "<query>", "type": "doc" })
// Create doc (MUST include description)
mcp_knowns_docs({ "action": "create", "title": "<title>",
"description": "<brief description of what this doc covers>",
"tags": ["tag1", "tag2"],
"folder": "folder"
})
// Update content
mcp_knowns_docs({ "action": "update", "path": "<path>",
"content": "content"
})
// Update metadata (title, description, tags)
mcp_knowns_docs({ "action": "update", "path": "<path>",
"title": "New Title",
"description": "Updated description",
"tags": ["new", "tags"]
})
// Update section only
mcp_knowns_docs({ "action": "update", "path": "<path>",
"section": "2",
"content": "## 2. New Content\n\n..."
})
Creating Documents
- Search first (avoid duplicates)
- Choose location:
| Type | Folder |
|---|---|
| Core | (root) |
| Guide | guides |
| Pattern | patterns |
| API | api |
- Create with title + description + tags
- Add content
- Validate after creating
CRITICAL: Always include description - validate will fail without it!
Updating Documents
Section edit is most efficient:
mcp_knowns_docs({ "action": "update", "path": "<path>",
"section": "3",
"content": "## 3. New Content\n\n..."
})
Validate After Changes
CRITICAL: After creating/updating docs, validate:
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 First seen · 160 lines · 20 tokens per session scan A cca96328dbe6
kn-doc is a skill published in the GitHub repository knowns-dev/knowns (249 stars, last pushed 22d ago), licensed MIT. It adds 20 tokens to every session and 1,098 once invoked, about $0.0001 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
printing-press-output-review
Internal sub-skill: agentic review of a printed CLI's sampled command output for plausibility issues that rule-based checks can't encode (substring-match relevance, format bugs, silent source drops, ranking failures). Invoked via the Skill tool by the main printing-press skill at Phase 4.85 and printing-press-polish…
autofix
Review and repair current local changes until they converge, or run Qwen Code Autofix issue and review workflows from GitHub Actions.
pr-babysitter
Use when monitoring GitHub pull request CI, diagnosing failed checks, rebasing branches onto github/main, applying narrowly scoped fixes, and updating PRs until their latest checks are green or a human blocker is identified.
audit
Fast quality gate — detects stack, runs static analysis, checks cross-layer consistency, fixes issues. Run between every pipeline phase, before every commit push, after every feature batch. Lighter than /analyze but catches the same critical issues.
logic-lens
AI-powered Claude Code skill that performs deep code review using formal logic and reasoning frameworks to detect bugs, anti-patterns, and security risks beyond what linters catch.
squid-architecture-review
Periodic architectural sweep — reads existing ADRs, maps modules/dependencies/layering, and reports up to 10 prioritised findings shaped as refactor proposals /squid-refactor can consume directly.