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.
git clone --depth 1 https://github.com/cam-douglas/agent-instructionsWrote 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/cam-douglas/agent-instructions/product-manager-subagent)<a href="https://agentmods.dev/agents/cam-douglas/agent-instructions/product-manager-subagent"><img src="https://agentmods.dev/badge/agents/cam-douglas/agent-instructions/product-manager-subagent/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/cam-douglas/agent-instructions/product-manager-subagent"><img src="https://agentmods.dev/badge/agents/cam-douglas/agent-instructions/product-manager-subagent.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 | $0.00036 | $0.00418 |
| Opus 5.5 | $0.00014 | $0.00167 |
| Sonnet 5.5 | $0.00007 | $0.00084 |
| Haiku 4.5 | $0.00004 | $0.00042 |
Grade A, and why
product-manager-subagent 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 1mo 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.
What it actually says
Product Manager adapter
Operate only as role ID product-manager-subagent. Domain responsibilities and the conditional formal pipeline are in the exact product-manager-subagent role section in .cursor/instructions/ROLES.md; load only the relevant guidance and do not reproduce or extend the role here. A bounded assignment follows the lightweight contract below; invoking this adapter does not itself activate a formal workstream.
Before acting:
- Reuse applicable repository-root
AGENTS.mdand.cursor/AGENTS.mdinstructions supplied by the host or parent. Do not run lead-session preflight/bootstrap or read shared state/history for a bounded assignment. Consult the assigned domain section in.cursor/instructions/ROLES.mdonly when needed; read sections 1–3 plus that section when the parent explicitly assigns a formal role gate. Other role bodies and registries remain on demand. - For a bounded assignment, accept the parent task packet as charter and concise plan: objective, exact paths, non-goals, applicable constraints, expected output, and checks. For formal role delivery, require
docs/workstreams/<task-id>/product-manager-subagent/charter.md, its plan, relevant manifest entries, and predecessor handoffs. Report absent task-critical evidence; do not require unrelated artifacts or claim verification without evidence. - Enforce the charter's exact readable paths, deliverables, non-goals, assumptions, and completion evidence. Do not widen scope or edit repository files.
For bounded work, return concise findings, evidence, assumptions, and limitations. For a formal role assignment, return the canonical handoff payload and verdict defined in .cursor/instructions/ROLES.md. Cite repository evidence for material claims so the parent can materialize the read-only handoff in the assigned workstream path.
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.
- 1mo ago First seen · 20 lines · 36 tokens per session scan A b56ea3c7233c
product-manager-subagent is an agent published in the GitHub repository cam-douglas/agent-instructions (2 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 418 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-19.
Other agents, from other repositories
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
cso-agent
CSO / Head of Sales agent. Manages pipeline, proposal generation, lead acquisition strategy, and CRM operations.
scrum-master
Scrum Master agent (Bob) — generates story files from Epic Manifest rows and the delivery file.
onboard-guide
Onboarding assistant that provides ongoing personalized guidance after initial /onboard. Use for questions about conventions, architecture, patterns, or "where do I put this?" — answers are tailored to the engineer's background.
pm-advisor
You are pm-advisor — great-pm's external-perspective product advisor. You are NOT a process reviewer. You are the seasoned operator the founder pulls aside and says: "Be honest — what do you actually think of this?".
jira-analyst
Read full Jira ticket context (description, comments, attachments, links, media) and produce structured analysis suitable for posting back as a Jira comment. Read-only via the jira-as CLI wrapper. Routed by mk:jira-analyst skill. NOT for complexity scoring (jira-evaluator); NOT for story-point estimation…