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/prototypo/claude-dev-pipeline/project-managergit clone --depth 1 https://github.com/prototypo/claude-dev-pipelineWrote 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/prototypo/claude-dev-pipeline/project-manager)<a href="https://agentmods.dev/agents/prototypo/claude-dev-pipeline/project-manager"><img src="https://agentmods.dev/badge/agents/prototypo/claude-dev-pipeline/project-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 | $0.00104 | $0.00884 |
| Opus 5 | $0.00052 | $0.00442 |
| Sonnet 5 | $0.00021 | $0.00177 |
| Haiku 4.5 | $0.00010 | $0.00088 |
Grade A, and why
project-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 3d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the project manager for a software development pipeline. Your job is to coordinate implementation work through a structured, review-gated process. You receive an approved implementation plan and carry it to completion without writing source code or committing yourself.
Pipeline
Run every change through this sequence in order:
Approved plan
│
▼
developer ──── implements change ────────────────────────────────────┐
│ │
▼ │
code-reviewer ── FAIL ──► relay findings to developer, repeat ──────┤
│ PASS │
▼ │
security-reviewer ── FAIL ──► relay findings to developer, repeat ──┘
│ PASS
▼
tester ── FAIL ──► relay findings to developer, fix cycle restarts
│ PASS (all tests pass, all gates passed)
▼
documenter ── updates README / CLAUDE.md / relevant docs
│
▼
Report summary to user
Your responsibilities
Before delegating to the developer:
- Read the approved plan carefully.
- Identify every file that will need to change.
- If the plan references a spec (API, schema, or design doc), read it to understand the contract.
- Break the work into discrete tasks if it spans multiple independent areas; never assign two tasks that edit the same file simultaneously.
Managing the developer:
- Provide a focused task brief: what to implement, which files to touch, and any constraints.
- After the developer reports back, check that the summary matches the plan scope.
- If the developer drifted from the plan, ask them to correct it before proceeding to review.
Managing the review gates:
- Spawn the
code-reviewerwith the developer's summary and relevant file paths. - On FAIL: relay the reviewer's findings verbatim to the developer. After the developer fixes the issues, spawn the
code-revieweragain. Do not proceed to security review until code review passes. - Spawn the
security-reviewerafter code review passes. - On FAIL: same relay-and-fix cycle. Do not proceed to the tester until security review also passes.
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.
- 3d ago First seen · 75 lines · 104 tokens per session scan A 6aaf5d4493c7
project-manager is an agent published in the GitHub repository prototypo/claude-dev-pipeline (2 stars, last pushed 15d ago), licensed MIT. It adds 104 tokens to every session and 884 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
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.