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 Sma1lboy/coforce-apply --skill profilegit clone --depth 1 https://github.com/Sma1lboy/coforce-applyWrote 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/sma1lboy/coforce-apply/profile)<a href="https://agentmods.dev/skills/sma1lboy/coforce-apply/profile"><img src="https://agentmods.dev/badge/skills/sma1lboy/coforce-apply/profile/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/sma1lboy/coforce-apply/profile"><img src="https://agentmods.dev/badge/skills/sma1lboy/coforce-apply/profile.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 | $0.00102 | $0.01881 |
| Opus 5.5 | $0.00041 | $0.00752 |
| Sonnet 5.5 | $0.00020 | $0.00376 |
| Haiku 4.5 | $0.00010 | $0.00188 |
Grade A, and why
profile 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 2mo 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Profile — local background maintenance
Single source of truth: ~/.coforce/profile.json (personal data — never in any
repo). The authoritative schema is the shape below. Never invent fields.
Shape (all fields optional): name, title, email, phone,
localizedContacts: Record<language, {email?, phone?}>, location,
linkedin, github, website, summary, skills[], courses[],
verifiedSkills[] {name, category?, source?, evidenceIds[]?, verifiedAt?},
resumeSkillPolicy {status: "review_requested" | "approved", baseline: string[], rolePacks: Record<string, string[]>, reviewedAt?: string | null},
experience[] {company, title, date, location?, url?, localized?: Record<language, partial entry metadata>, description[{text, textZh?, weight?, source?, verifiedAt?}], weight?},
education[] {institution, degree, date, location?, relevantCourses?},
projects[] {name, role?, url?, demo?, localized?: Record<language, partial entry metadata>, description[{text, textZh?, weight?, source?, verifiedAt?}], technologies?, dateRange?, weight?, repo?{url?, path, headSha, investigatedAt}},
certifications[] {name, issuer, date}, languages[] {language, proficiency},
customSections[] {title, weight?, entries[{heading?, subheading?, date?, description?[{text, textZh?, weight?, source?, verifiedAt?}]}]}
— user-defined resume sections (Awards, Publications, Leadership, Open Source…)
that tailor renders as additional sections when relevant.
weight (higher = more important) drives what gets picked when tailoring a resume
to a JD — set it when the user signals importance, otherwise omit.
Operations
Init (~/.coforce/profile.json missing):
- Create
~/.coforce/if needed. If the user has an existing resume (PDF/JSON/text), read it and map into the schema. - A resume that lands here gets an intake review — the material the user
arrived with becomes the pool every future resume is selected from, so it is
worth knowing what a screener sees in it before building on top. Run it per
the
campaignskill'sreferences/resume-judge.md, Intake mode section (sibling install; fresh subagent, never this one — a parser that has read the rubric writes to it). It gates nothing and it runs AFTER whatever the user actually came for:tailor's front door delivers the PDF first, then this. Skip it entirely if the user only asked to edit one field. - Point the user at the console's Profile tab (tracker skill, port 4517) as the friendly editing surface: structured form (basics, skill chips, experience/project/education cards with per-bullet editing), a skill-policy review ledger, plus an "Import resume (AI)" button that parses pasted text via the local agent runtime for review-then-save.
- Otherwise interview briefly: contact basics → education → experience → projects → skills. Don't interrogate; accept partial data, everything is optional.
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.
- 2mo ago First seen · 132 lines · 102 tokens per session scan A f6e9509b2c5c
profile is a skill published in the GitHub repository Sma1lboy/coforce-apply (5 stars, last pushed 1mo ago), licensed MIT. It adds 102 tokens to every session and 1,881 once invoked, about $0.0004 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.