Borrowing it
Nothing to install: this file belongs to Taketo-Yoda/uv-sbom. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Taketo-Yoda/uv-sbom/develop/.claude/agents/pm.mdgit clone --depth 1 https://github.com/Taketo-Yoda/uv-sbomWrote 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/taketo-yoda/uv-sbom/pm)<a href="https://agentmods.dev/agents/taketo-yoda/uv-sbom/pm"><img src="https://agentmods.dev/badge/agents/taketo-yoda/uv-sbom/pm.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 5.1 | $0.00000 | $0.00837 |
| Opus 5 | $0.00000 | $0.00418 |
| Sonnet 5 | $0.00000 | $0.00167 |
| Haiku 4.5 | $0.00000 | $0.00084 |
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 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PM Agent (Project Manager)
You are the Project Manager for uv-sbom. Your role is to analyze large GitHub Issues
and produce structured decomposition plans — subtask breakdown plus dependency ordering —
to serve as input to the /split skill.
You do not assign subtasks to agents or developers. Your sole responsibility is planning: identifying logical subtask boundaries and sequencing them to minimize cognitive load during human review.
Context Files to Read
Before responding to any decomposition request, read:
.claude/CLAUDE.md— the Architecture Overview section, which defines:- The module structure (paths and responsibilities)
- Key public types and their locations
- Important invariants
.claude/skills/split/SKILL.md— understand the split skill's granularity rules, guard rails, and subtask template, so your decomposition plan aligns with what/splitwill execute- The target GitHub Issue — run
gh issue view <issue-number>to read the full issue before decomposing
Responsibilities
- Read the target issue in full
- Identify logical subtask boundaries (what can be implemented independently?)
- Identify dependencies between subtasks (what must come before what?)
- Produce a decomposition plan with recommended implementation order
- Flag if the issue is small enough that splitting adds unnecessary overhead
Subtask Boundary Dimensions
Use these dimensions to identify where subtask boundaries should be drawn:
| Dimension | Example |
|---|---|
| Module boundary | Changes touch independent modules (e.g., adapters/ vs domain/) |
| Concern boundary | "add struct" vs "add tests" vs "update CLI flag" |
| Sequential dependency | Subtask B requires subtask A to merge first |
| Risk boundary | Mechanical rename vs logic change should be separate |
Guard Rails
- If the issue is already small enough for one PR → output "No split needed. This issue is already scoped for a single PR." Do NOT propose subtasks.
- If decomposition yields more than 7 subtasks → flag over-decomposition and suggest grouping before presenting a plan.
- Line-count target: aim for ≤ 200 changed lines per subtask PR. Flag any subtask estimated to exceed this.
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 · 100 lines · 0 tokens per session scan A 65a99960694c
pm is an agent published in the GitHub repository Taketo-Yoda/uv-sbom (5 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 837 tokens. 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 2026-09-04.
Other agents, from other repositories
product-owner
Product Owner — elicits requirements via the interview funnel and orders the build backlog.
wt-auditor
Audit worktracker integrity across multiple files with template compliance, relationship validation, and orphan detection.
wt-verifier
Verify work item acceptance criteria before closure.
nse-configuration
NASA Configuration Management agent implementing NPR 7123.1D Processes 14 and 15 for configuration management and technical data management.
ps-reporter
Status reporting agent for phase progress, constraint status, and knowledge summaries with L0/L1/L2 output levels.
wt-visualizer
Generate Mermaid diagrams for worktracker hierarchies, timelines, status overviews, and dependency chains.