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.
git 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/commands/jananthan30/resume-builder/job-fit)<a href="https://agentmods.dev/commands/jananthan30/resume-builder/job-fit"><img src="https://agentmods.dev/badge/commands/jananthan30/resume-builder/job-fit/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/commands/jananthan30/resume-builder/job-fit"><img src="https://agentmods.dev/badge/commands/jananthan30/resume-builder/job-fit.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 | $0.00014 | $0.01025 |
| Opus 5.5 | $0.00006 | $0.00410 |
| Sonnet 5.5 | $0.00003 | $0.00205 |
| Haiku 4.5 | $0.00001 | $0.00103 |
Grade A, and why
job-fit 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 1mo 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Job Fit Pre-Screen — Deterministic GO/NO-GO Gate
Evaluate the configured master resume against this exact job description before any resume work begins.
Input
$ARGUMENTS
CANDIDATE-FIT PREFLIGHT (MANDATORY FIRST GATE)
-
Read
config.jsonand resolve its exactmaster_resume_path. This configured master is the only resume allowed in the assessment. Never use a previous tailored resume, application resume, or “best match” template. -
Put the exact job description in a private temporary UTF-8 file. Do not create an application/output directory, resume draft, DOCX, or tracker row.
-
Generate one safe
run_id, one safecase_id, and one strict ISO calendaras_of_date, then capture the sole intended machine output from:python candidate_fit_preflight.py --resume <configured-master-resume> --job-description <private-exact-JD.txt> --run-id <run_id> --case-id <case_id> --as-of-date <YYYY-MM-DD> --json -
Parse only the JSON report. Require
schema_version: "1.0.0",policy_version: "candidate-fit-policy-v3",scorer_version: "evidence-match-v1", the exact run/case IDs and date, exact master/JD SHA-256 digests, exactthreshold: 70.0, all seven named component scores, a booleanextraction_trustworthy,hard_knockouts,passed, and orderedcodes. Recompute the canonical JSON SHA-256 and display it ascandidate_fit_report_digest. -
Proceed status is valid only when the process exits
0,score >= 70, extraction is trustworthy,hard_knockoutsis empty,passedis true, andcodesis empty. No dimension, recommendation, ATS score, HR score, or user preference can compensate for a failed condition. -
Exit
1, any score below 70, or any hard knockout isREJECTED:CANDIDATE_FIT. Exit2or an unavailable, malformed, non-canonical, stale, or digest-mismatched report isFAILED:CANDIDATE_FIT_PREFLIGHT. Both fail closed and authorize no tailoring, role/native-team invocation, output, DOCX, or tracker operation.
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.
- 1mo ago First seen · 95 lines · 14 tokens per session scan A d35cbdbcb1ed
job-fit is a command published in the GitHub repository jananthan30/Resume-Builder (87 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 1,025 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
job-search
Search live IT vacancies on freehire and shortlist the ones worth applying to.
tailor-cv
Reframe a CV toward one vacancy, citing evidence for every claim.
triage-inbox
Sort application mail into the freehire tracker and drain the link queues.
market-fit
Score a stack against live vacancy demand and name the gaps worth closing.
track-applications
Review where every application stands and bring the tracker up to date.
start
Onboard with Rebound — capture your base resume and build your private profile (skills, differentiators, and situation).