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-extractgit 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-extract)<a href="https://agentmods.dev/skills/knowns-dev/knowns/kn-extract"><img src="https://agentmods.dev/badge/skills/knowns-dev/knowns/kn-extract/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-extract"><img src="https://agentmods.dev/badge/skills/knowns-dev/knowns/kn-extract.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 | $0.00018 | $0.00930 |
| Opus 5.5 | $0.00007 | $0.00372 |
| Sonnet 5.5 | $0.00004 | $0.00186 |
| Haiku 4.5 | $0.00002 | $0.00093 |
Grade A, and why
kn-extract 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Extracting Knowledge
Announce: "Using kn-extract to extract knowledge."
Core principle: CAPTURE ONLY GENERALIZABLE KNOWLEDGE, WITH PROVENANCE.
Inputs and Modes
- Completed task ID, code change, repeated pattern, or recurring failure
--consolidateto review existing learning docs instead of extracting one source
Use Knowns APIs for managed tasks, docs, memories, and decisions. Do not edit their markdown directly.
Normal Extraction
1. Read the Source
Read the task or referenced work and identify genuine findings in three categories:
| Category | Capture when |
|---|---|
| Pattern | A reusable implementation, architecture, integration, or process approach exists |
| Retrospective learning | A good call, bad call, surprise, trade-off, or failure can improve future work |
| System Decision | Stable guidance future work must follow: architecture, behavior, naming, storage, API contract, workflow convention, or explicit trade-off |
Do not fabricate findings. A valid no-op is better than generic advice.
2. Search Before Creating
Search docs, memories, and current Decisions for overlap. Prefer updating a canonical doc over creating a duplicate.
mcp_knowns_search({ "action": "search", "query": "<topic>", "type": "doc" })
mcp_knowns_search({ "action": "search", "query": "<topic>", "type": "memory" })
3. Persist the Right Artifact
- Pattern or detailed learning: create/update a Knowns doc and link the source task/doc.
- Fast recall: save a concise project Memory that links the canonical doc. Use only
pattern,convention,preference, orfailurecategories. - Stable guidance: create a first-class draft System Decision candidate with task/doc/source provenance. Never auto-accept it.
- Generatable pattern: create a template only when repeated generation is genuinely useful and a linked pattern doc exists.
Never create Memory category decision. Spec Decisions remain canonical in an approved spec's Locked Decisions section and must not be copied into the System Decision ledger.
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 · 99 lines · 18 tokens per session scan A f79677cbacdc
kn-extract is a skill published in the GitHub repository knowns-dev/knowns (248 stars, last pushed 22d ago), licensed MIT. It adds 18 tokens to every session and 930 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
alive:save
The human wants to checkpoint. Or: the stash has grown heavy — 5+ items, 30+ minutes, a natural pause in the work. The squirrel doesn't decide when to save. It surfaces the need and lets the human pull the trigger. Runs the full save protocol: confirms stash, writes log, updates state, generates projections…
alive:capture-context
Use when external content arrives in the session — emails, transcripts, screenshots, documents, files, or in-session research worth keeping. Also use when there's nothing obvious to capture — the skill checks 03Inbox/ for unrouted files and enters inbox scan mode. Stores raw content, routes to bundles, extracts tasks…
alive:session-history
Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…
alive:load-context
The human mentions a walnut to work on, asks about a specific venture/experiment/project, or wants to check status — not just explicit 'load X'. Load the brief pack (3 files), resolve the people involved, check the active bundle — then surface one observation and ask what to work on. Context loads in tiers: walnut and…
alive:mine-for-context
Deep context extraction from source material. Creates reference bundles, builds extraction plans, tracks what's been extracted, and discovers new targets — people, subjects, patterns, connections. The archaeologist that turns raw sources into structured knowledge. Can be invoked by alive:session-history for targeted…
alive:my-context-graph
Render an interactive map of your world. Generates the world index from all walnut and bundle frontmatter, then produces a force-directed graph showing connections between walnuts, people, bundles, and tags. Opens in the browser.