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/lexler/skill-factory/extract-knowledgenpx skills add lexler/skill-factory --skill extract-knowledgegit clone --depth 1 https://github.com/lexler/skill-factoryWrote 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/lexler/skill-factory/extract-knowledge)<a href="https://agentmods.dev/skills/lexler/skill-factory/extract-knowledge"><img src="https://agentmods.dev/badge/skills/lexler/skill-factory/extract-knowledge.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 | $0.00026 | $0.01167 |
| Opus 5 | $0.00013 | $0.00583 |
| Sonnet 5 | $0.00005 | $0.00233 |
| Haiku 4.5 | $0.00003 | $0.00117 |
Grade A, and why
extract-knowledge 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
STARTER_CHARACTER = 📝
Extract Knowledge
Turn what a session knows into prose that stands alone. The reader is a stranger: they were not in the session and they see only the text. Each lens below defends the stranger against one distortion.
Seats
Decide which seat you are in — it changes what you can verify.
- Author seat: you did the work, so the knowledge is in your context. You can verify faithfulness directly, but you are half-blind to standalone failures because you cannot un-know the session. Compensate deliberately: reread the draft as the stranger, asking of every referent "do I know this if I only have the text?"
- Reviewer seat: the argument points at text someone else wrote. You are the stranger, so standalone and prose failures are visible to you directly. For faithfulness, check claims against the source session or transcript if one is reachable; mark the claims you cannot verify instead of guessing.
Steps
-
Read the argument. A topic means extract that topic. No argument means extract everything important. Existing text or a file path means take the reviewer seat and go straight to the lens gate.
-
Draft the extraction. Capture what the session learned: decisions with their why, corrections and preferences the user stated, insights discovered, dead ends that cost time, and questions still open. Done when every insight in scope is either in the draft or consciously judged not worth the reader's time.
-
Run the lens gate below and keep a visible verdict list: a bulleted list, one lens per line — its name, then "clean" or the defect found and fixed. A verdict names a defect caught in the draft; a lens that shaped the draft from the start still reports "clean". A lens without a verdict line was skipped, not passed. Done when the verdict list covers every lens in all three groups.
-
Output the text in chat, or return it if another agent invoked you. Persistence belongs to the caller: hand over prose, and let the caller decide if and where it becomes a file. The extracted text is the only artifact — the verdict list and any questions to the user are chat output, and stay out of the text however it is saved or passed on.
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 · 60 lines · 26 tokens per session scan A de7008d0fdc1
extract-knowledge is a skill published in the GitHub repository lexler/skill-factory (231 stars, last pushed 8d ago), licensed Apache-2.0. It adds 26 tokens to every session and 1,167 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
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
auditing-subgroup-fairness
Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…