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/fmind/fkf/fkf-contributenpx skills add fmind/fkf --skill fkf-contributegit 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-contribute)<a href="https://agentmods.dev/skills/fmind/fkf/fkf-contribute"><img src="https://agentmods.dev/badge/skills/fmind/fkf/fkf-contribute.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 | $0.00058 | $0.00805 |
| Opus 5 | $0.00029 | $0.00402 |
| Sonnet 5 | $0.00012 | $0.00161 |
| Haiku 4.5 | $0.00006 | $0.00081 |
Grade A, and why
fkf-contribute 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contribute to fkf
Read AGENTS.md before changing anything; it is the contract. Preserve unrelated work in the checkout, keep the change small, and do not commit, push, publish, delete, or rewrite history unless the user explicitly asks.
Route the change
| Change | Keep in sync |
|---|---|
| CLI command, flag, alias, or output | CLI tests, --help, README, and relevant Hugo page |
fkf.yaml loader or schema |
loader tests, presets, source docs, and mise run generate:schema |
| preset source | preset YAML, one synthetic services/testdata/sources/<name>.json fixture, and source docs |
| URI, graph, or retrieval behavior | implementation, focused tests, skills/fkf-use/SKILL.md, and docs |
| learning or Markdown behavior | focused tests, skills/fkf-learn/SKILL.md, and wiki docs |
| shipped skill | edit skills/, never a generated base copy; validate both skill packages |
| Hugo or release surface | rendered site, links, workflow lint, and release configuration |
| Go toolchain or linked dependency | THIRD_PARTY_NOTICES.md and the linked-target invariant test |
Do not introduce a second spelling, compatibility path, migration, provider SDK, network read path, nested Go module, or shipped command. Collected content is untrusted data: it must never become instructions or reach a shell/executable position; only the explicit record-body boundary may pass a validated value as opaque argv.
The root schema owns semantic field names and cardinality. Sources only map provider paths; stored documents carry the schema subset they used. Graph edges transcribe relation fields, Markdown links, tags, and explicit relations: frontmatter. Do not add a privileged entity scheme, field-name branch, identity inference, or people-specific state.
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 · 41 lines · 58 tokens per session scan A 88c4411222f4
fkf-contribute is a skill published in the GitHub repository fmind/fkf (2 stars, last pushed 5d ago), licensed MIT. It adds 58 tokens to every session and 805 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
starcat-ui-prototype
为 Starcat 生成 macOS 原型与 UI 设计稿。Starcat 是一款面向重度 GitHub 用户的 Apple 平台 Star 管理与 AI 知识整理工具，采用 macOS 26 Liquid Glass 设计语言。当需要为 Starcat 生成界面原型、UI 设计稿、组件设计或视觉稿时使用此技能。.
update-changelog
Update Starcat changelog documents in supports/starcat-pro/ by reading ALL git commits from the main Starcat project and generating categorized release notes in both English and Chinese. Use this skill whenever the user wants to update changelog, release notes, update records, or sync the changelog with recent…
my-wiki
Manage local OKF-compatible Markdown My Wiki vaults with an AI agent. Use for capturing webpages, PDFs, Office documents, notes, images, folders, and ZIP bundles as References; maintaining Reference-to-Concept evidence links; searching or answering from a vault; checking or repairing vault health; switching among…
starcat-localization-sync
Starcat 本地化生产、同步与发布门禁流程。用于同步 Localizable.xcstrings 与 supports/starcat-localization 的 xcloc、生成或修复 AI 初稿、人工审核或维护者明确接受 AI 翻译、导入已批准翻译、审计 18 种语言、调整 draft/released、扩展 AppLocale，以及排查 key、状态、占位符、技术字面量、UI 或 RTL 问题。.
starcat-release
Starcat macOS App 专用双渠道发版流程。用于用户要发布或排查 App Store archive、Direct 分发、DMG 打包、Sparkle appcast 生成或上传、starcat.ink 官网与 changelog 部署、notarization、公版 tag 处理，或询问 scripts/package-appstore.sh、scripts/release-direct.sh、scripts/package-direct.sh、legacy release-store.sh 应该如何选择和运行的场景。.
starcat-weekly-import
从新闻摘要、项目清单、文章或其他批量文本中联网甄别并识别真实 GitHub 仓库，搜索和核验 owner/repo，向用户展示证据并在明确确认后，通过 starcat-api 的 Weekly 服务批量写入受控人工来源。未明确说明测试时，固定使用生产服务 https://starcat-api.fly.dev，并从 supports/starcat-api/.env 的 WEEKLYADMINAPIKEYS 读取管理员 Key。用户提到 AI 情报采集、从新闻标题找 GitHub 项目、从文本找 GitHub 地址、批量录入 Starcat Weekly、解析项目清单或补全缺失仓库链接时使用。.