uv-sbom: Agent for Claude Code

.claude/agents/pm.md

pm is an agent for Claude Code from Taketo-Yoda/uv-sbom. It costs 0 tokens per session (837 once invoked), scanned A, original, MIT.

A project-planning agent for breaking a large GitHub Issue into smaller tasks and ordering them by dependency. It prepares a plan for a separate tool to carry out.

In plain words
What is it for?
Use it to read an issue, identify independent subtasks, and show which tasks must come first.
Why use it?
Large issues can be difficult to review and implement as one piece. This separates the work into logical steps without assigning tasks to people or agents.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions CLAUDE.md.

This is Taketo-Yoda/uv-sbom's own configuration. It tells Claude Code how to work on uv-sbom itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything uv-sbom configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/Taketo-Yoda/uv-sbom/develop/.claude/agents/pm.md
Clone the repo
git clone --depth 1 https://github.com/Taketo-Yoda/uv-sbom

Made for: Claude Code.

Wrote 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.

agentmods badge for pm

README.md
[![agentmods](https://agentmods.dev/badge/agents/taketo-yoda/uv-sbom/pm.svg)](https://agentmods.dev/agents/taketo-yoda/uv-sbom/pm)
Your own site
<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>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 837 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 3d ago against content hash 65a99960694c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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.

.claude/agents/pm.md · 100 lines

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:

  1. .claude/CLAUDE.md — the Architecture Overview section, which defines:
    • The module structure (paths and responsibilities)
    • Key public types and their locations
    • Important invariants
  2. .claude/skills/split/SKILL.md — understand the split skill's granularity rules, guard rails, and subtask template, so your decomposition plan aligns with what /split will execute
  3. 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.

Read the full file on GitHub · 100 lines

Changes

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.

  1. 3d ago First seen · 100 lines · 0 tokens per session scan A 65a99960694c

Subscribe to this mod's changes

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.