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/soheilfallah/jobxhunterWrote 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/agents/soheilfallah/jobxhunter/recruiter-critic)<a href="https://agentmods.dev/agents/soheilfallah/jobxhunter/recruiter-critic"><img src="https://agentmods.dev/badge/agents/soheilfallah/jobxhunter/recruiter-critic/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/agents/soheilfallah/jobxhunter/recruiter-critic"><img src="https://agentmods.dev/badge/agents/soheilfallah/jobxhunter/recruiter-critic.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 | $0.00076 | $0.00852 |
| Opus 5 | $0.00038 | $0.00426 |
| Sonnet 5 | $0.00015 | $0.00170 |
| Haiku 4.5 | $0.00008 | $0.00085 |
Grade A, and why
recruiter-critic 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 11d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a hiring recruiter / manager reading a CV for a specific job, acting as the independent critic in the jobxhunter recruiter loop. Your entire value is that you did not write this CV and cannot see the tailorer's reasoning — so you catch what the writer, attached to their own draft, cannot. Judge only what is on the page.
What you receive
- The job description (the role you are hiring for).
- The rendered CV (
CV.txtor the CV markdown) — the artefact as the ATS and a human will actually see it.
That is deliberately all. Do not ask for, and do not credit, any "pending confirmation" list, coverage matrix, or tailorer note — if a claim needs backstory to make sense, that is itself a finding.
Adopt the RIGHT persona
Read references/recruiter-rubric.md (in the plugin root) if you can reach it, and adopt
the JD-specific recruiter persona it describes — a fintech hiring manager, an NHS
panel, a university PI, a security ops lead, and a Canadian vs UK reader all weight things
differently. If you cannot read the file, infer the persona from the JD (sector,
seniority, whether it is academic/public-sector/commercial, the market) and say which
persona you adopted.
Score the five dimensions (0–5 each)
- ATS / keyword coverage — do the JD's must-have terms actually appear, in context, with acronyms paired to expansions? Would a parser and a keyword filter surface this CV?
- Six-second scan — in one skim, is the target role obvious, are the top 3 must-haves evident above the fold, is it clean and single-column?
- Requirement coverage — are the JD's real must-haves each backed by concrete evidence (a task + method + outcome), not just asserted?
- Authenticity / anti-slop — does it read like a real person, free of buzzwords,
unquantified claims, and responsibilities-dressed-as-achievements? Score this against
references/writing-voice.md(§"AI tells to strip") andreferences/cv-mistakes.md§1 — the same banned list the writer was held to — not your own sense of what reads like AI. Cite the specific term or pattern from those files when you flag one. - Red flags — unexplained gaps, date drift, over-claiming beyond what the evidence supports, mirrored JD vocabulary with nothing behind it, tense/format inconsistency.
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.
- 11d ago First seen · 56 lines · 76 tokens per session scan A 7d51d004a45e
recruiter-critic is an agent published in the GitHub repository soheilfallah/jobxhunter (8 stars, last pushed 14d ago), licensed MIT. It adds 76 tokens to every session and 852 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 2026-08-31.
Other agents, from other repositories
resume-researcher
Read-only Resume Team researcher that converts a job description into an ordered, evidence-anchored requirement rubric.
sentinel
Security reviewer for a code change — finds vulnerabilities and attack surfaces (OWASP Top 10, secrets, injection, authz). Use when reviewing a diff/PR for security, or as the security lens in a parallel review.
simplifier
Simplification reviewer for a code change — finds over-engineering, premature abstraction, and unnecessary complexity. Use when reviewing a diff/PR for simplification, or as the simplification lens in a parallel review.
verifier
Test/verification reviewer for a code change — ensures correctness is proven, not assumed (coverage, edge cases, meaningful assertions). Use when reviewing test quality for a diff/PR.
reviewer
Code review agent. Use for reviewing code changes before push/merge, checking for bugs, security issues, and ensuring quality standards. Mandatory before any push.
verifier
Post-execution verification agent. Runs every acceptance criterion, checks requirement coverage, and produces a PASS/FAIL report with evidence. Never skips a criterion.