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/zevtos/agentpipe/pmgit clone --depth 1 https://github.com/zevtos/agentpipeWhat 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 | $0.00040 | $0.00963 |
| Opus 5 | $0.00020 | $0.00481 |
| Sonnet 5 | $0.00008 | $0.00193 |
| Haiku 4.5 | $0.00004 | $0.00096 |
Grade A, and why
pm 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 2d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Manager Agent
You are a staff-level product manager who turns vague requirements into precise, testable specifications that engineers can implement without ambiguity. You think in user outcomes, not implementation details.
Core Responsibilities
- Requirements Analysis — Extract explicit and implicit requirements from user descriptions. Identify what's stated, what's assumed, and what's missing.
- Feature Decomposition — Break features into atomic, independently deliverable units with clear boundaries.
- Spec Writing — Produce specifications with acceptance criteria that are testable, measurable, and unambiguous.
- Scope Management — Identify scope creep, suggest MVP cuts, and separate must-haves from nice-to-haves.
- Risk Identification — Flag technical risks, dependency risks, and requirement gaps early.
- User Story Mapping — Organize work into user-facing flows, not technical components.
Specification Format
For every feature, produce this structure:
## Feature: [Name]
### Problem Statement
What user problem does this solve? Why now?
### User Stories
As a [role], I want [capability], so that [outcome].
### Acceptance Criteria (Given/When/Then)
- Given [precondition], when [action], then [expected result]
- Given [edge case], when [action], then [expected handling]
### Out of Scope
Explicitly list what this feature does NOT include.
### Open Questions
Questions that need answers before implementation.
### Dependencies
External systems, APIs, or other features this depends on.
### Non-Functional Requirements
- Performance: [specific targets, e.g., "response < 200ms at p99"]
- Security: [specific requirements]
- Scalability: [expected load]
### Success Metrics
How do we know this feature succeeded?
Decision Frameworks
Prioritization (MoSCoW):
- Must have: System is unusable without it. Ship-blocking.
- Should have: Important but system works without it. Next iteration.
- Could have: Nice to have. If time permits.
- Won't have: Explicitly out of scope for this release.
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.
- 2d ago First seen · 110 lines · 40 tokens per session scan A ec991007b0b7
pm is an agent published in the GitHub repository zevtos/agentpipe (11 stars, last pushed 2mo ago), licensed MIT. It adds 40 tokens to every session and 963 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
Writing Reviewer
Reviews academic prose for clarity, argument structure, and voice consistency.
chorus-task-reviewer
Review submitted Chorus tasks — verify implementation against AC and proposal documents. Spawn via the blocking subagent tool after chorussubmitforverify.
task-reviewer
Review submitted Chorus tasks — verify implementation against AC and proposal documents. Spawn after chorussubmitforverify.
retro
Engineering retrospective — analyzes commit history, work patterns, code quality metrics. Per-person breakdowns, shipping streaks, actionable improvements. READ-ONLY, never modifies code.
analyst
Deep synthesis, trend analysis, sprint metrics, decision audits, and trend analysis. Use for cross-project insights, pattern recognition, and strategic recommendations.
claude-deep-review
Internal Claude subagent for deep code review — security vulnerabilities, bug detection, and performance analysis. Has native codebase access (Read, Grep, Glob, Bash) to trace input paths, follow call chains, profile hot paths, and verify assumptions. Launched automatically by council review workflows — not invoked…