Borrowing it
Nothing to install: this file belongs to Sma1lboy/coforce-apply. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Sma1lboy/coforce-apply/main/.agents/skills/start/SKILL.mdgit 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/start)<a href="https://agentmods.dev/skills/sma1lboy/coforce-apply/start"><img src="https://agentmods.dev/badge/skills/sma1lboy/coforce-apply/start/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/start"><img src="https://agentmods.dev/badge/skills/sma1lboy/coforce-apply/start.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 | $0.00074 | $0.01696 |
| Opus 5.5 | $0.00030 | $0.00678 |
| Sonnet 5.5 | $0.00015 | $0.00339 |
| Haiku 4.5 | $0.00007 | $0.00170 |
Grade A, and why
start 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Start — one discover→resume-review cycle
Setup must exist (~/.coforce/config.json, or a legacy
apply-config.json/preferences.json pair — those migrate on first read);
missing → run the setup skill first. Read ~/.coforce/instructions.md
before anything else — it overrides every default below.
The console's Discover tab is the interactive twin of discovery: postings queued there become pending tracker entries and campaign dossiers. Treat them as first in line for resume generation.
Cycle
-
Discover (the script ships with this skill, path relative to this skill's base directory):
node "<skill-dir>/scripts/hunt.mjs" --trackFetches all configured sources, skips anything already tracked (URL or company+role match — never double-apply), anything already screened out (see step 2) and every
never-applycompany, tracks the rest aspendingwith a discovery history event. Report the summary (new / already-tracked / screened / blocked). -
Filter for fit: read
~/.coforce/config.json(canonical user intent — level, directions,needsSponsorship,workMode,locations,salaryFloor; schema in the setup skill) plusinstructions.md. From the newpendingentries, drop ones that clearly contradict either (wrong level, no-sponsorship posting whenneedsSponsorshipis true, onsite-only whenworkModeis remote, excluded location):node "<skill-dir>/scripts/hunt.mjs" screen <url> --reason "<why>"That takes the posting out of
applications.jsonand records it in the screening ledger instead. Never give a screened job a status — least of allrejected, which means a company turned the user down; a board that mixes the two lies about how the search is going. Discovery dedups against both ledgers, so a screened posting never comes back on its own, andhunt.mjs unscreen <url>reverses the call. Report how many were screened and why.Two hard gates run before soft fit judgment, and both quote the posting rather than paraphrasing it:
- Eligibility gate: a posting that names a citizenship / permanent-
residency requirement or a security clearance, against a config that
says
needsSponsorship: true→ screen it out (hunt.mjs screen <url> --reason "<the quoted line>"), never a pipeline status: the reason quotes the exact requirement ("must be a US citizen"). Quoting matters: the user may know something about their status the config doesn't, and a verbatim quote lets them overrule from the board. Silence on citizenship is NOT a fail — silence is not permission, but it's not a rejection either; the posting proceeds unverified. - Language gate: a posting requiring, as a job condition, a language the profile doesn't carry at all → screen it out with the quoted line as the reason. Required language present but the stated bar ("fluent", "native", "C1") plausibly exceeds the profile's level → flag, don't drop: keep the entry, note the quoted requirement in the tracker entry so it surfaces at review. Judge the ad's language separately from the role's working language — a Danish-language ad for an English-working role passes.
- Eligibility gate: a posting that names a citizenship / permanent-
residency requirement or a security clearance, against a config that
says
What ships with it
1 file 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.
- 2mo ago First seen · 129 lines · 74 tokens per session scan A ebe492d1d459
start is a skill published in the GitHub repository Sma1lboy/coforce-apply (5 stars, last pushed 1mo ago), licensed MIT. It adds 74 tokens to every session and 1,696 once invoked, about $0.0003 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.