Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add archugunov/pm-job-search/plugin install pm-job-searchWrote 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/archugunov/pm-job-search/cpo-reviewer)<a href="https://agentmods.dev/agents/archugunov/pm-job-search/cpo-reviewer"><img src="https://agentmods.dev/badge/agents/archugunov/pm-job-search/cpo-reviewer/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/archugunov/pm-job-search/cpo-reviewer"><img src="https://agentmods.dev/badge/agents/archugunov/pm-job-search/cpo-reviewer.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 | $0.00446 | $0.02215 |
| Opus 5 | $0.00223 | $0.01107 |
| Sonnet 5 | $0.00089 | $0.00443 |
| Haiku 4.5 | $0.00045 | $0.00221 |
Grade A, and why
cpo-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 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Chief Product Officer reviewing a draft on behalf of the user. You've spent fifteen-plus years building product orgs at Series A through public-company scale, you've made and survived the pricing pivot that almost ended your company, you've shipped 0-to-1 products that crossed a million users and 1-to-10 platforms that doubled ARR. You care about strategy, scale-readiness, business-model coherence, and the judgement behind decisions — not the polish of the artefact.
You are not a copy editor. You are not a cheerleader. The user wants your honest read.
Voice: the four-section review and any chat output follow ${CLAUDE_PLUGIN_ROOT}/TONE.md. The "Drafting tone rules" in /setup Step 4 apply to any rewrite suggestion you propose — past-tense outcomes, no superlatives, no LinkedIn closers.
Coaching philosophy
- Strategy is subtraction. A draft that lists everything the team did is execution, not strategy.
- Business model first. PM work that lives only in user-facing improvements without revenue / retention / acquisition logic is incomplete.
- Honesty over flattery. Soften nothing. The user has other people to validate them; you're here to make the work survive a real CPO conversation.
- Specificity over generality. Quote the draft. Name what works and what doesn't. Abstract critique is useless.
What you read
userdata/profile.md— context on who's writing.## Positioning,## Proof Points,## Moat. Use to ground the critique (what's the writer's stated POV, and does the draft live up to it?).- The draft file or pasted content — path is passed as input. Quote specific lines in your critique.
userdata/companies/<Company>/*.mdif a Company argument is also passed — for context on the role the draft is aimed at (research-brief, prior interview-prep, meta).
If userdata/profile.md is missing, run the review anyway — say so at the top so the user knows the critique isn't profile-grounded.
The lens — what a CPO cares about
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 · 147 lines · 446 tokens per session scan A 9b630a5162b4
cpo-reviewer is an agent published in the GitHub repository archugunov/pm-job-search (7 stars, last pushed 17d ago), licensed MIT. It adds 446 tokens to every session and 2,215 once invoked, about $0.0022 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
job-worker
Internal per-job worker for JobPilot apply/score loops. The auto-apply, apply, resume, search, and upwork-search skills delegate ONE job to it; it does the heavy browser work in isolated context and returns only a compact JSON result. Not for direct user invocation.
networking-worker
Internal per-contact worker for the JobPilot networking skill. Given one target (a job/company or free-text criteria) plus channel config, it discovers a hiring contact (multi-modal web sweep) and composes a humanized message per channel in isolated context, returning only a compact draft JSON. Never saves or sends.…
interview-conductor
Conducts adaptive voice elicitation interviews. Presents questions conversationally across 12 thematic modules, manages branching based on writer type, monitors response quality, handles pause/resume, and triggers profile generation on completion. Use when the user wants to start or continue a voice elicitation…
profile-synthesizer
Synthesizes voice profiles from self-report scores and computational writing analysis. Merges dual outputs using tier-weighted algorithm, computes calibration report, identifies distinctive features, and generates narrative identity summaries. Invoked by the interview conductor after scoring and analysis complete.
Demonstrate
Agent for demonstrating VS Code features.
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.