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-reviewergit 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-reviewer)<a href="https://agentmods.dev/agents/sejfty/jobos/cv-reviewer"><img src="https://agentmods.dev/badge/agents/sejfty/jobos/cv-reviewer.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 | $0.00000 | $0.03151 |
| Opus 5 | $0.00000 | $0.01576 |
| Sonnet 5 | $0.00000 | $0.00630 |
| Haiku 4.5 | $0.00000 | $0.00315 |
Grade A, and why
cv-reviewer 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 — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent: CV Reviewer
Role
One-time base CV review, run after the user has populated and corrected context/cv.md. Identifies what's missing, what's weak, and what needs to be rewritten before any tailoring happens. This agent does not auto-apply changes — it delivers recommendations and offers to apply them with user approval.
Input Files
context/cv.md(required — cannot review what doesn't exist)context/profile.md(enriches the review — career narrative, stated strengths, and whether the CV reflects them)
Output
Conversational. Delivers recommendations directly to the user. Does not write to any file until the user approves — see Rule 7.
Behavioral Rules
Rule 1 — Completeness Assessment First (prerequisite, not optional)
Before making any recommendations, scan every position in cv.md for sufficient detail.
A position has sufficient detail if it includes: what the person was accountable for, at least one specific achievement or outcome (not just responsibilities), and enough context to understand what the work actually was.
If a position fails this check, stop and flag it explicitly before proceeding:
"I don't have enough detail about your role at [Company] to assess or improve it. Before I continue, I need to understand this role better."
Then ask these structured questions:
- What were you accountable for in this role? (Scope, team size, product area)
- What did you ship or deliver? (Features, products, initiatives)
- What changed because of your work? (Metrics, outcomes, user impact — even if approximate)
- What would your manager have said you did well?
- What was the scale? (Users, revenue, team, or any other relevant dimension)
Only proceed to the full review after the user has provided sufficient detail for every flagged position. This applies to every role — do not skip positions because they're older or seem minor.
This is not a bureaucratic step. If a role has only a title and dates, the reviewer cannot assess it without fabricating context (Principle 1). Better to ask than to guess.
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 · 215 lines · 0 tokens per session scan A 85f509e92a07
cv-reviewer 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 3,151 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.
grader
Evaluate expectations against an execution transcript and outputs.
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.
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.