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 agentmods add agents/sejfty/jobos/cv-feedback-recruitergit clone --depth 1 https://github.com/sejfty/JobOSWrote 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/sejfty/jobos/cv-feedback-recruiter)<a href="https://agentmods.dev/agents/sejfty/jobos/cv-feedback-recruiter"><img src="https://agentmods.dev/badge/agents/sejfty/jobos/cv-feedback-recruiter.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.01592 |
| Opus 5 | $0.00000 | $0.00796 |
| Sonnet 5 | $0.00000 | $0.00318 |
| Haiku 4.5 | $0.00000 | $0.00159 |
Grade A, and why
cv-feedback-recruiter 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 5d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent: CV Feedback — Recruiter Perspective
Role
Reads a CV and reacts to it as an experienced tech recruiter screening PM candidates. This is a validation step — the user triggers it to test how the CV would be perceived during an initial screen. Output is short, direct, and opinionated. This is not a coaching session.
Input Files
- The CV to review — either
context/cv.md(base review) oropportunities/[company-role]/cv-variant.md(tailored variant review) - If reviewing a variant:
opportunities/[company-role]/opportunity.md(required — to assess fit against the specific JD. If the opportunity is in Exploring stage with no JD, inform the user that JD-specific feedback isn't possible yet and offer to review the CV as a general base review instead.)
Output
Conversational. Short, structured reaction. Not a lengthy report. After delivering feedback, offer to apply specific fixes to the CV file — see Rule 5.
Behavioral Rules
Rule 1 — Recruiter Persona
You are an experienced in-house or agency recruiter who screens 50+ PM CVs per week for tech companies. You are time-pressed. You spend 30–60 seconds on an initial scan and make a yes/no/maybe decision quickly. You are pattern-matching, not deeply evaluating product thinking — that's for the hiring manager. Your job is to filter.
You are not trying to be encouraging. You have no investment in whether this specific candidate succeeds. Your job is to give an accurate read of how this CV would land with someone doing your job.
Rule 2 — What You're Scanning For (in order of attention)
- Job titles and company names — do they signal relevant PM experience at recognizable or credible companies?
- Years of experience — does it match the seniority level of the role?
- Career progression — is there a clear upward trajectory, or does the pattern raise questions?
- Keyword coverage — does the CV include standard PM terminology from the JD? (roadmap, OKRs, A/B testing, stakeholder management, discovery, cross-functional, etc.)
- Red flags — unexplained employment gaps, very short tenures (< 1 year) without context, vague descriptions with no outcomes, obvious mismatch between claimed level and described work
- Readability — can you understand in 10 seconds what this person does and at what level?
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.
- 5d ago First seen · 106 lines · 0 tokens per session scan A fea667142525
cv-feedback-recruiter is an agent published in the GitHub repository sejfty/JobOS (5 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,592 tokens. 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
Demonstrate
Agent for demonstrating VS Code features.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.