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/harness/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/harness)<a href="https://agentmods.dev/skills/sma1lboy/coforce-apply/harness"><img src="https://agentmods.dev/badge/skills/sma1lboy/coforce-apply/harness/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/harness"><img src="https://agentmods.dev/badge/skills/sma1lboy/coforce-apply/harness.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 | $0.00082 | $0.01292 |
| Opus 5.5 | $0.00033 | $0.00517 |
| Sonnet 5.5 | $0.00016 | $0.00258 |
| Haiku 4.5 | $0.00008 | $0.00129 |
Grade A, and why
harness 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harness — mock E2E
Repo-development skill — it needs the coforce-apply repo checkout
(harness/ fixtures), so installers skip it; end users don't need it.
Everything runs against fixtures; the user's real ~/.coforce/profile.json is
never touched. Mock environment lives in harness/:
harness/fixtures/profile.json— John Doe fixture (schema:profileskill)harness/fixtures/reference.docx— reference resume for the docx pathharness/fixtures/applications.json— tracker fixture (5 apps across statuses)harness/fixtures/agent-stub.sh— stand-in for the Claude Code CLI (COFORCE_CLAUDE_BIN), so apply/import flows run without a real agentharness/mock/jd.html— mock job posting (Nimbus Analytics, Senior Full-Stack)harness/check-formats.sh/check-github-evidence.py/check-config.mjs/check-experience.mjs/check-campaign.mjs/check-board.mjs/check-hunt.mjs— deterministic checks (all seven run in order vianpm run harness; the repo has no npm dependencies, so a bare checkout can run them)harness/out/— run artifacts (gitignored)
Stages (run all, report per-stage pass/fail)
1. Resume generation (the "出简历" leg).
Run the tailor skill's steps with harness/fixtures/profile.json as the
profile and harness/mock/jd.html as the JD, writing to
harness/out/resume-nimbus-analytics-senior-full-stack.tex. Then verify, by
reading the output: it is valid-looking LaTeX (\documentclass …
\end{document}), contains the fixture's name and email, and leads with
JD-relevant skills (TypeScript/React/Node.js/AWS/Kubernetes appear before
unrelated ones). Fail the stage if any check misses.
Also exercise the alternate output/reference paths: regenerate the docx leg
(markdown intermediate → pandoc → .docx in harness/out/) and read
harness/fixtures/reference.docx back as a reference (mimic check: extraction
succeeds and output honors its section order).
2. Deterministic checks (formats, evidence, config, experience, campaign, board, hunt).
npm run harness
Asserts: docx reference extraction and md→docx round-trip work; the vendored
GitHub evidence layer holds its attribution/pagination/writer guardrails and
the experience index rebuilds offline; config.json migrates off the legacy
settings pair without losing keys and refuses to overwrite a corrupt file;
the campaign pipeline selects verbatim pool bullets and exports the approved
ZIP; when Tectonic is present (always in CI), it also assembles and compiles one
English and one Chinese resume through the real LaTeX→PDF→pdftotext path,
requiring localized contacts, complete selected bullets/skills, and ATS reading
order; the board generator renders all 5 status columns and fixture cards from
harness/fixtures/applications.json, rejects a never-apply company at
/api/queue,
and the console's Chrome-backed apply lifecycle runs consent gate → fill
(READY_TO_SUBMIT) → confirm → SUBMITTED against the agent stub; hunt
parses, dedups against the tracker, and honors the never-apply list.
Exit code 0 = pass.
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 · 93 lines · 82 tokens per session scan A 9d56bcb87c11
harness is a skill published in the GitHub repository Sma1lboy/coforce-apply (5 stars, last pushed 1mo ago), licensed MIT. It adds 82 tokens to every session and 1,292 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
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.