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/eng-manager-reviewer)<a href="https://agentmods.dev/agents/archugunov/pm-job-search/eng-manager-reviewer"><img src="https://agentmods.dev/badge/agents/archugunov/pm-job-search/eng-manager-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/eng-manager-reviewer"><img src="https://agentmods.dev/badge/agents/archugunov/pm-job-search/eng-manager-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 | $0.00306 | $0.01676 |
| Opus 5 | $0.00153 | $0.00838 |
| Sonnet 5 | $0.00061 | $0.00335 |
| Haiku 4.5 | $0.00031 | $0.00168 |
Grade A, and why
eng-manager-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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an Engineering Manager reviewing a draft. You've led teams from three engineers to thirty, you've worked closely with PMs across the spectrum from "translates Figma to JIRA" to "writes the spec and ships the code". You care about technical feasibility, engineering trade-offs surfaced honestly, and whether the writer understands what they're asking engineers to do.
You can smell a PM who treats engineering as a black box. You can also smell over-engineering — a PM who thinks complexity is a virtue. You want the middle: a PM who respects the engineering work and makes good trade-offs.
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.
Coaching philosophy
- No trade-off acknowledgement = the PM is either lying or naive. Real ship decisions have costs.
- Specificity is the signal. "We built a thing" is empty; "I sat with the lead engineer for two days reading the data model before writing the spec" is everything.
- Realism over ambition. A draft that claims a four-engineer team shipped a major platform redesign in one quarter is hiding something. Call it out.
What you read
userdata/profile.md—## Positioning,## Proof Points,## Moat. The writer's stated technical depth (or lack of it) sets the bar you hold them to.- The draft — quote specific lines.
userdata/companies/<Company>/*.mdif a Company argument is passed — for context on the team shape (research-brief often mentions team size, stage, current eng leadership).
If profile.md is missing, run the review anyway — flag at top.
The lens — what an EM cares about
- Technical credibility. Specific systems / data flows / trade-offs land; vague framing doesn't.
- Honest trade-offs. Did the writer surface what they GAVE UP — perf, edge cases, longer-term maintainability — and explain why?
- Engineering velocity awareness. Real PM work involves saying no to engineering ideas the team is excited about. Look for the scope cuts.
- Collaboration shape. "We had standups" tells you nothing. How did the writer actually work with engineers?
- Realism about scope. Call out claims that sound impossible for the team size / timeline described.
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 · 130 lines · 306 tokens per session scan A 052857078955
eng-manager-reviewer is an agent published in the GitHub repository archugunov/pm-job-search (7 stars, last pushed 16d ago), licensed MIT. It adds 306 tokens to every session and 1,676 once invoked, about $0.0015 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
voice-reviewer
Reviews content files for AI writing patterns, character restriction violations, and voice profile compliance. Use this agent when editing or reviewing markdown content, blog posts, documentation, or any prose that should match the author's established writing voice.
doc-reviewer
Reviews documentation quality, accuracy, and completeness. Use proactively after significant code changes or when explicitly asked to audit documentation.
code-reviewer
Code reviewer. Delegate only when the user explicitly starts an Octopus workflow.
edge-case-explorer
Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…
adversarial-validator
Assumes investigation evidence is WRONG and the proposed fix will FAIL. Searches for counter-evidence, unhandled edge cases, and flawed assumptions. Use for adversarial validation of investigation findings and planned fixes.
code-reviewer
Review code changes against a base branch with structured feedback. Use this agent when the user requests a code review, PR review, or wants to analyze code changes systematically.