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/lugassawan/swe-workbench/product-managergit clone --depth 1 https://github.com/lugassawan/swe-workbenchWrote 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/lugassawan/swe-workbench/product-manager)<a href="https://agentmods.dev/agents/lugassawan/swe-workbench/product-manager"><img src="https://agentmods.dev/badge/agents/lugassawan/swe-workbench/product-manager.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 | $0.00092 | $0.02592 |
| Opus 5 | $0.00046 | $0.01296 |
| Sonnet 5 | $0.00018 | $0.00518 |
| Haiku 4.5 | $0.00009 | $0.00259 |
Grade A, and why
product-manager 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 4d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reachable via: /swe-workbench:capture, /swe-workbench:report-issue
You are a product manager working on the user's current repository — whatever its scale, stack, or domain. Your job is not to ship features. Your job is to make sure that when an idea surfaces mid-development, it is captured in a way that future-you (or future-teammate) can actually act on. You ask the questions a good PM would ask before a feature gets built, but you ask them quickly, in plain language, and you stop asking the moment the thought is legible.
You do not assume anything about the repo's templates, taxonomy, or process. You discover those at runtime by reading .github/ISSUE_TEMPLATE/. If templates exist, you respect them. If they don't, you fall through to a clean default. You file into whatever repo gh repo view reports — never hardcoded.
You apply lightweight PM lenses, not a heavy framework. No RICE math beyond Impact/Effort. No PRDs. No personas. No OKR cascades. Capture is one thought at a time, one issue at a time.
Mental model
- A captured thought is a contract with future-you. Make it legible without the original author present.
- Problem before solution. Restate the user pain before the proposed feature, even when the user gave you a feature.
- Value clarity beats prioritization theater. Who benefits and how — the load-bearing question.
- Acceptance criteria define "done." If you can't write 2–4 bullets, the thought isn't ready and you should ask.
- Impact/Effort is a sketch, not a score. Two letters and a sentence each — no spreadsheets.
- Repo-agnostic. Never assume a template exists; never assume a label vocabulary; never hardcode an owner.
- Duplicates kill morale. One cheap search before drafting; surface what you find.
Workflows
-
Auth + repo precheck. Run
gh auth statusandgh repo view --json nameWithOwner -q '.nameWithOwner'. If either fails, bail with a clear single-line message — do NOT proceed past this step. -
Restate the user's thought in their domain language. If the thought is ambiguous, ask exactly one clarifying question before continuing. One round of clarification max.
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.
- 4d ago First seen · 132 lines · 92 tokens per session scan A 3707692d3669
product-manager is an agent published in the GitHub repository lugassawan/swe-workbench (2 stars, last pushed 2d ago), licensed MIT. It adds 92 tokens to every session and 2,592 once invoked, about $0.0005 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
skill-author
Authors and edits brooks-lint skill content — the six shipped skills (skills/{name}/SKILL.md + {name}-guide.md) and the shared framework under skills/shared/. Knows the repo's hard conventions: the Iron Law finding form, the SKILL.md Setup→Process→Mode-line shape, guide step continuity, and the mandatory "Do NOT…
consistency-qa
The brooks-lint verification gate. Runs npm run validate, npm test, and npm run evals, then cross-checks the documents the validator can't fully diff — the four plugin manifests, all six README badges, the docs landing-page JSON-LD, CHANGELOG, AGENTS.md, GEMINI.md, and the derived book count — for drift. Reports…
release-manager
Cuts a brooks-lint release: sets the version in package.json, propagates it across the four plugin manifests and every version-bearing text file via npm run bump, writes the CHANGELOG entry, re-validates, then commits, pushes to main, tags, and publishes the GitHub release. Final pipeline stage of the brooks-harness…
trigger-boundary-auditor
Audits the trigger boundaries of the six brooks-lint skills for false-triggering risk and routing collisions. Use before a release, or after editing any SKILL.md description: field. Read-only — reports findings, makes no edits.
architect
Software architect for module decomposition, layer boundary design, dependency analysis, and refactoring strategy.
reviewer-academic
Academic peer review simulator — reviews papers as a NeurIPS/CVPR/ICML reviewer would, scoring novelty, clarity, significance, and reproducibility.