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 agentmods add skills/knowns-dev/knowns/kn-extractnpx 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.svg" alt="Measured on agentmods" 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 | $0.00018 | $0.00930 |
| Opus 5 | $0.00009 | $0.00465 |
| Sonnet 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 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.
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.
- 4d 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 (242 stars, last pushed today), licensed MIT. It adds 18 tokens to every session and 930 once invoked, about $0.0001 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.
Other skills, from other repositories
agent-session-monitor
Real-time agent conversation monitoring - monitors Higress access logs, aggregates conversations by session, tracks token usage. Supports web interface for viewing complete conversation history and costs. Use when users ask about current session token consumption, conversation history, or cost statistics.
trellis-brainstorm
Guides collaborative requirements discovery before implementation. Creates task directory, seeds PRD, asks high-value questions one at a time, researches technical choices, and converges on MVP scope. Use when requirements are unclear, there are multiple valid approaches, or the user describes a new feature or complex…
fullenrich-content-engagers
Use when the user says "enrich people who engaged with this post", "qualify post engagers with FullEnrich", "scrape and enrich LinkedIn post {URL}", "engagers from this post into a CSV", "enrich this CSV of leads", "FullEnrich content engagers", or any variant indicating they want to convert a list of leads — either…
architecture-reviewer
Use when making architectural decisions, planning features, designing new components, reviewing PRs, or validating that proposed changes align with Clean Architecture principles. Triggers include "review architecture", "check design", "does this fit", "where should this go", "planning a feature", or before…
enrich-with-signals
Pull PredictLeads buying-intent signals (jobs, news, funding, tech, leadership changes) for a result set of companies and write them back into the local cache. Use when the user says 'enrich these companies with signals', 'add buying signals to this list', 'pull intent data for [domain]', 'check signals for these…
alive:system-upgrade
Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.