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/sma1lboy/coforce-apply/setupnpx skills add Sma1lboy/coforce-apply --skill setupgit clone --depth 1 https://github.com/Sma1lboy/coforce-applyWhat 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 | $0.00161 | $0.02457 |
| Opus 5 | $0.00081 | $0.01229 |
| Sonnet 5 | $0.00032 | $0.00491 |
| Haiku 4.5 | $0.00016 | $0.00246 |
Grade A, and why
setup 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 2d 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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup — one-time onboarding
Everything lands in the CoForce data home — ~/.coforce/ by default (create
it first: mkdir -p ~/.coforce). Run stages in order, skip any that are
already complete. Batch questions per stage — don't drip.
0. Data home — local-only or private-fork sync
Wherever this skill (or any skill) says ~/.coforce, the actual home is
resolved as: $COFORCE_HOME env override → <checkout>/.coforce/ if it
exists → ~/.coforce. Two supported modes; ask which the user wants (default
local-only):
- Local-only (default):
~/.coforce/on this machine. Nothing to do. - Private-fork sync: the user forked this repository, made the fork
PRIVATE, and keeps their data inside the checkout at
.coforce/— profile, tracker, instructions, and archives then sync across machines through their fork (git pullon the other machine), andgit pull upstream mainkeeps the tool itself current.
Enabling private-fork mode has an IRON GATE — verify before creating anything:
git remote get-url originmust NOT be the canonical public repo (Sma1lboy/coforce-apply) — data in a clone of the public repo can never be pushed anywhere safe.gh repo view --json isPrivate -q .isPrivatemust printtrue. Ifghis unavailable or there is no remote yet, STOP and make the user confirm explicitly that the remote is (or will be) private before continuing. Refusal is the default: when in doubt, stay local-only.
Once verified: mkdir -p .coforce in the checkout, then append exactly this
block to the END of the repo's .gitignore (later patterns override the
public-checkout guard above them):
# coforce private-fork mode — fork verified private; data home syncs in-repo
!/.coforce/
/.coforce/out/
Tell the user what does NOT sync: out/ (regenerable artifacts) and ATS
passwords (macOS Keychain only, never files — re-register or re-enter
credentials per machine). Committing and pushing the data home is the user's
normal git flow afterwards; skills never auto-push.
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.
- 2d ago First seen · 198 lines · 161 tokens per session scan A 01157cff5e8f
setup is a skill published in the GitHub repository Sma1lboy/coforce-apply (5 stars, last pushed 3d ago), licensed MIT. It adds 161 tokens to every session and 2,457 once invoked, about $0.0008 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
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
lark-im
飞书即时通讯：收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片（Interactive Card）、监听卡片按钮回调（card.action.trigger）。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶（添加/移除/查询置顶会话）、管理标签数据、处理卡片回调时使用。.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
reflect
Review recent work, find repeated workflow patterns, and suggest reusable skills, agents, commands, config changes, or playbooks. Use when the user asks to learn from past sessions, improve recurring workflows, or identify what should be turned into reusable agent instructions.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
organize-threads
猫猫辅助整理未分类 thread，分析标题和元数据，建议合适的标签。 Use when: 用户说"帮我整理"、"分类 thread"、点击整理按钮。 Not for: 删除/编辑标签本身。 Output: 按 thread 的标签建议列表。.