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 jananthan30/Resume-Builder --skill resume-teamgit clone --depth 1 https://github.com/jananthan30/Resume-BuilderWrote 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/jananthan30/resume-builder/resume-team)<a href="https://agentmods.dev/skills/jananthan30/resume-builder/resume-team"><img src="https://agentmods.dev/badge/skills/jananthan30/resume-builder/resume-team/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/jananthan30/resume-builder/resume-team"><img src="https://agentmods.dev/badge/skills/jananthan30/resume-builder/resume-team.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00071 | $0.01752 |
| Opus 5 | $0.00036 | $0.00876 |
| Sonnet 5 | $0.00014 | $0.00350 |
| Haiku 4.5 | $0.00007 | $0.00175 |
Grade A, and why
resume-team 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 12d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resume Team
-
Resolve the plugin root two directories above this file. Require macOS or Linux,
candidate_fit_preflight.py,native_resume_team.py,config.json, and the configured master resume. Fail closed if any is unavailable. Put the exact job description in a private temporary UTF-8 file, and generate a saferun_id, safecase_id, and strict ISOas_of_date. Before invoking the native team or creating an output directory, screen onlymaster_resume_pathfromconfig.json(never a previous tailored resume):python candidate_fit_preflight.py --resume <CONFIGURED_MASTER> --job-description <PRIVATE_EXACT_JD.txt> --run-id <RUN_ID> --case-id <CASE_ID> --as-of-date <YYYY-MM-DD> --jsonContinue only on exit
0and a valid digest-boundcandidate-fit-policy-v3report with threshold70.0, score at least70, trustworthy extraction, zero hard knockouts,passed: true, and no codes. Canonically hash the exact report ascandidate_fit_report_digest. Exit1, any score below 70 (including 60–69), or any hard knockout isREJECTED:CANDIDATE_FIT; report it and create no output, draft, DOCX, or tracker row. Exit2or an unavailable, malformed, stale, non-canonical, or digest-mismatched report isFAILED:CANDIDATE_FIT_PREFLIGHT. Neither condition has a bypass. ATS/HR scores are advisory and cannot override candidate fit. -
Only after candidate fit passes, run the non-model host preflight. Windows is not supported by the hardened runtime; its host preflight returns
POSIX_RUNTIME_REQUIRED:python native_resume_team.py --host codex --check-host --config config.jsonContinue only when it exits
0and returnsready: truewith every check passing. -
Choose only a prospective new output path. Use a user-supplied path only when it does not exist; otherwise derive a sanitized, non-existing
applications/<Company> - <Role>path from the job description. Do not create it. Never reuse, replace, or clobber an existing output orresume.md; the runtime intentionally has no replacement mode. -
Capture the runtime's exact stdout in a private temporary result file so the result-provided authorization sidecar path and digest remain available to finalization:
runtime_result_file="$(mktemp)"; python native_resume_team.py --host codex --job-description-file <PRIVATE_EXACT_JD.txt> --output-dir <APP_DIR> --config config.json --run-id <RUN_ID> --case-id <CASE_ID> --as-of-date <YYYY-MM-DD> >"$runtime_result_file"Preserve and check the Python process exit status before parsing the single JSON result from that file. Do not reconstruct result fields from logs or filenames. The runtime independently recomputes the same fit report before constructing an output or role adapter. Require its report and canonical digest to exactly match the caller-validated preflight. Only then does it create
<APP_DIR>and atomically bind that exact text to<APP_DIR>/job_description.txt; it accepts only a byte-identical pre-existing regular file and never clobbers a different one. The Researcher contract admits only nonblank, alphanumeric requirements that each cover one exact, unique, complete non-separator JD line; substrings are rejected so surrounding negation, scope, bounds, and qualification cannot be trimmed before the Writer or Auditor sees the rubric.Omit
--modeland--reasoning-effortby default. The hardened subprocess ignores user configuration and transient parent-session settings, so report its effective model/reasoning selection as the isolated managed CLI default and unknown—not as an inherited model, Ultra setting, or profile. Only when the user explicitly requests a Codex pin may you append--model <exact-model>and/or--reasoning-effort ultra. There is no runtime profile or replacement option; always choose a new output directory and fail closed rather than clobber an existing artifact. -
Accept draft-stage success only when the process exits
0, the captured result isresume-team-result/v2withterminal_class: PUBLISHED, itscandidate_fit_reportandcandidate_fit_report_digestexactly match the independently validated preflight, and<APP_DIR>/resume.mdexists with the reportedfinal_draft_digest. Independently hashresume.md. Resolve the exactauthorization_receipt_pathfrom that result against<APP_DIR>when relative and require the resolved path's parent to equal the resolved output directory. Then invoke the code-bound acceptance gate with the exact result-provided digest and require exit0plusverified: true:
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.
- 12d ago First seen · 90 lines · 71 tokens per session scan A 27ed31bd84f8
resume-team is a skill published in the GitHub repository jananthan30/Resume-Builder (83 stars, last pushed 28d ago), licensed MIT. It adds 71 tokens to every session and 1,752 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
freehire-job-search
Use when finding IT jobs for someone — searching or filtering the freehire catalogue by keyword, region, seniority, skills, salary or company; reading a posting or a company's open roles; discovering what values a filter accepts; reading the saved job-search profile before asking someone what they want; handing over a…
freehire-mail-triage
Use when sorting a job seeker's application mail into the freehire tracker from their own mail client (himalaya, mbsync, notmuch, the Gmail API, any IMAP) — pushing a fetched batch, judging what each message is, linking it to an application, advancing a stage from a reply, or draining the two queues the matcher fills…
freehire-tailor-cv
Use when reframing someone's CV toward a specific vacancy through freehire — reading the fit analysis for a tailored copy, fetching or editing the CV document by path, rendering the ATS PDF, or deciding what may and may not be written into a CV. Carries the evidence rule: anything stating what the candidate DID needs…
freehire-market-fit
Use when measuring a set of skills — a CV's stack, or one skill on its own — against live open-vacancy demand on freehire; when telling a candidate which in-demand skills they are missing and what learning each would unlock; or when gauging how much of a filtered market (a role, a region, a seniority) their current…
freehire-track-applications
Use when recording or reviewing what someone applied to on freehire — marking a job applied, bookmarking one for later, moving an application through its stages (applied through offer, or rejected/withdrawn), attaching a note, or listing what they are tracking. Also covers reporting a posting that never answered them…
lockedin-audit
Scores any resume or cover letter against LockedIn's calibrated rubric. No vault required. Three modes: score, refine, refine then score. Activate when the user says "audit my resume", "score my resume", "check my resume", or provides a resume file and asks for feedback. Also triggered after a completed lockedin…