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 fmind/fkf --skill fkf-learngit clone --depth 1 https://github.com/fmind/fkfWrote 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/fmind/fkf/fkf-learn)<a href="https://agentmods.dev/skills/fmind/fkf/fkf-learn"><img src="https://agentmods.dev/badge/skills/fmind/fkf/fkf-learn/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/fmind/fkf/fkf-learn"><img src="https://agentmods.dev/badge/skills/fmind/fkf/fkf-learn.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 | $0.00043 | $0.00720 |
| Opus 5.5 | $0.00017 | $0.00288 |
| Sonnet 5.5 | $0.00009 | $0.00144 |
| Haiku 4.5 | $0.00004 | $0.00072 |
Grade A, and why
fkf-learn 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 23d 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.
What it actually says
fkf-learn
Knowledge is Markdown in the base; Git keeps its history. Keep each note short and current so the next session can act on it.
- Select the intended base and audience. Find the owning note with
fkf search --base NAME. Prefer updating it over creating a new one. Read it fully before editing; resolve the base path before using filesystem tools. - Choose the place: a project's state, decisions and next actions in
projects/<project>.md; reusable knowledge inwiki/<concept>.md; a delegated or multi-session job intasks/YYYY-MM-DD_slug/TASK.mdwithinputs/andoutputs/; a repeated procedure in the base'sskills/. - Edit in place. Replace outdated statements instead of appending history sections; add a dated one-line entry under
## Decisionsfor each decision, with its reason and a ref to the evidence ([meeting](source:id)). Setupdated: YYYY-MM-DD. - Only write what you verified or the user stated. Mark proposals as proposals. Never invent provenance, verification or dates.
- When records disagree, compare upstream revision time, observation time and declared collection coverage; do not silently turn a partial or historical record into a current fact. Promote only reviewed, shareable summaries into a team base, with evidence teammates can access.
- Run
fkf validate --base NAMEand fix problems introduced by the edit; report unrelated failures without deleting evidence to pass a check. When the edit changes an answer the base should retain, add or update itsqueries.yamlcase and runfkf eval --base NAME.fkf statuslists active or blocked project notes due forreview(not updated for 14 days); refresh one when you touch its project. Show the diff; commit only when the user's standing instructions allow it.
Project notes follow this shape:
---
type: project
status: active # active | paused | blocked | done | archived
updated: 2026-09-22
summary: One sentence on what this project is for.
aliases: [repo:github.com/owner/name]
---
# Project
Intent in two or three sentences.
## Now
Current state in a short paragraph, with links to canonical documents or repositories.
## Decisions
- 2026-09-22: decision, because reason ([evidence](source:id)).
## Next actions
- [ ] The single most important next step.
Wiki concepts follow OKF v0.2 (template): a type, status: draft|stable|deprecated, sources as mappings with a resource, and verified only for real checks with by and at. Keep wiki/index.md a short list of entry points. Tasks start from the task template and keep a Resume section with the exact next action.
Replace sample dates, identities and refs with verified values. Do not rewrite collected records to make a note true; update the authored interpretation and retain its evidence.
After substantial work, recommend one concrete update to the user when it would save a future session time: what to change, where, and why.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 23d ago Changed · +25 lines · +7 tokens per session 58281c8b4c6e
- 26d ago Changed · +4 lines 955a33b20b9b
- 1mo ago Changed · -78 lines · -1 tokens per session 5e670861a14c
- 1mo ago Changed · +2 lines bff61390f996
- 1mo ago Changed · +4 lines · -3 tokens per session 9d47cf8b19d7
- 1mo ago Changed · -15 lines · -7 tokens per session bcd9570e96d4
- 1mo ago First seen · 109 lines · 47 tokens per session scan A c4b9a19e7d8c
fkf-learn is a skill published in the GitHub repository fmind/fkf (3 stars, last pushed 23d ago), licensed MIT. It adds 43 tokens to every session and 720 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
any-mcp
Use when an agent needs to read, search, create, edit, organize, upload, or chat with Anytype through the bounded any-mcp server. Covers safe tool selection, exact identifier chaining, optional toolsets, common PKM workflows, and the narrow anyr fallbacks for chat subscriptions and rich chat blocks.
memorywhale
Query and write durable debugging memory recorded by MemoryWhale. Use when debugging a failure that may have happened before, when you need the exact error/flags/output from an earlier attempt, when the user asks "how did we fix this last time?", or once you've figured out why something failed / how a fix worked and…
recall
Use Recall to search, inspect, continue, export, resume, or share indexed AI coding sessions. Trigger for project-history lookup, recent work from other agents, file history, unfinished-session continuation, and published session-page management.
reflect
Use Recall Reflect to review AI coding workflow history as a conversation-first timeline and discuss observed patterns before changing behavior. Trigger when the user asks to reflect on a project, review AI coding workflow, inspect workflow friction, discuss repeated corrections, review handoffs, or explore possible…
douyin-favorites-to-knowledge
A tool for copying videos saved in an authorised Douyin account into a local Markdown or Obsidian knowledge base. Douyin is a Chinese short-video platform, and Obsidian is an app for organising linked notes.
memorywhale-evidence
Use MemoryWhale debugging evidence when the user requests recall or a recurring failure may have relevant recorded history.