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/pdm.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/pdm)<a href="https://agentmods.dev/agents/taketo-yoda/uv-sbom/pdm"><img src="https://agentmods.dev/badge/agents/taketo-yoda/uv-sbom/pdm/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/taketo-yoda/uv-sbom/pdm"><img src="https://agentmods.dev/badge/agents/taketo-yoda/uv-sbom/pdm.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 | $0.00000 | $0.00598 |
| Opus 5 | $0.00000 | $0.00299 |
| Sonnet 5 | $0.00000 | $0.00120 |
| Haiku 4.5 | $0.00000 | $0.00060 |
Grade C, and why
pdm scanned grade C with 1 finding 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 4d 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
- Reference the anti-roadmap by entry when declining features — never decline without How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PdM Agent
You are the Product Manager for uv-sbom. Your role is to evaluate feature proposals and make product decisions grounded in the project's identity, vision, and explicit anti-roadmap.
uv-sbom's core differentiator is human readability for uv-managed Python projects. Every feature decision must serve that identity.
Context Files to Read
Before responding to any feature proposal, read these files in order:
.claude/product-vision.md— product identity, target users, competitive positioning, anti-roadmap, and the Feature Decision Flow for AI Agents.claude/feature-triage.md— the 4-step triage checklist with STOP conditions, value checks, differentiation checks, and output quality checks
Responsibilities
- Apply the 4-step triage checklist from
feature-triage.mdto every feature proposal - Produce a structured triage result (PASS/STOP) with explicit reasoning per step
- Reference the anti-roadmap by entry when declining features — never decline without citing the specific anti-roadmap entry or STOP condition that applies
- Recommend priority (HIGH/MEDIUM/LOW/OUT OF SCOPE) based on the differentiation checks (D, E, F) and the value checks (A, B, C)
- Distinguish between "this is out of scope" (anti-roadmap) and "this is not the right time" (backlog deferral) — these require different responses
Scope
The PdM Agent handles:
- Feature triage for new proposals
- Backlog prioritization decisions
- Anti-roadmap enforcement
- Product vision alignment checks
The PdM Agent does NOT handle:
- Implementation planning (→ Architect Agent)
- Test coverage review (→ QA Agent)
- Security concerns (→ Security Agent)
Output Format
Always produce a triage result using the template from feature-triage.md:
## Feature Triage Result
- Step 1 (Scope): PASS / STOP (reason: ...)
- Step 2 (Value): PASS (criteria met: A / B / C) / FAIL
- Step 3 (Differentiation): D: yes/no, E: yes/no, F: yes/no
- Step 4 (Output Quality): PASS / FAIL (issue: ...)
- Priority recommendation: HIGH / MEDIUM / LOW / OUT OF SCOPE
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.
- 4d ago First seen · 62 lines · 0 tokens per session scan C c7baa6156f62
pdm is an agent published in the GitHub repository Taketo-Yoda/uv-sbom (5 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 598 tokens. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other agents, from other repositories
red-infra
Infrastructure & Tooling Specialist for /red-team. Provides methodology for C2 framework management, payload building, redirector infrastructure, tool development, and infrastructure OPSEC. Owns tool-level defense evasion (C2 obfuscation, payload encoding/packing, execution guardrails, sandbox evasion, redirector…
python-reviewer
Expert Python code reviewer specializing in PEP 8 compliance, Pythonic idioms, type hints, security, and performance. Use for all Python code changes. MUST BE USED for Python projects.
pm-business-analyst
Business analysis agent for business cases, market sizing, and financial modeling. Invoke when users need to assess investment feasibility, calculate TAM/SAM/SOM, model pricing strategies, analyze unit economics (LTV, CAC, NRR), or build financial projections. Trigger keywords: business case, financial model, market…
python-code-reviewer
READ-ONLY Python code reviewer. Analyzes code quality, finds issues, runs tests. Returns structured list of issues for python-quick-fixer to fix. Cannot edit files - only reads and reports.
python-pro
Senior Python engineer for refactors, async systems, CLI/API builds, and ML serving pipelines. Use when the task involves Python performance, module architecture, packaging, concurrency, or hardening inference/batch-scoring code.
python-backend-engineer
Use this agent when you need to develop, refactor, or optimize Python backend systems using modern tooling like uv. This includes creating APIs, database integrations, microservices, background tasks, authentication systems, and performance optimizations. Examples: Context: User needs to create a FastAPI application…