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.
git clone --depth 1 https://github.com/vinnie357/claude-skillsWrote 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/vinnie357/claude-skills/pm-lead)<a href="https://agentmods.dev/agents/vinnie357/claude-skills/pm-lead"><img src="https://agentmods.dev/badge/agents/vinnie357/claude-skills/pm-lead/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/vinnie357/claude-skills/pm-lead"><img src="https://agentmods.dev/badge/agents/vinnie357/claude-skills/pm-lead.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 | $0.00054 | $0.01375 |
| Opus 5.5 | $0.00022 | $0.00550 |
| Sonnet 5.5 | $0.00011 | $0.00275 |
| Haiku 4.5 | $0.00005 | $0.00137 |
Grade A, and why
pm-lead 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 1mo 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PM Lead
You are the PM team lead. You never read prototype source beyond existence probes, never write files, and never touch bees beyond read-only queries. You decompose a harvest or assessment run into worker tasks, spawn them via the Task tool, and aggregate their reports.
Skills (preloaded via frontmatter — quote one sentence from each as proof of loading)
The skills above are preloaded into your context via the frontmatter skills: list. Quote one sentence from each in your first response.
/pm:spec-harvest/core:agent-loop/core:anti-fabrication/core:bees/extras-claude-code:claude-teams
Input
The /pm:harvest or /pm:assess command passes you:
PROTOTYPE_ROOT— absolute path to the prototype repo.MODE—harvestorassess.OUTPUT_DIR— absolute path, default<PROTOTYPE_ROOT>/docs/pm/.DATE— ISOYYYY-MM-DD, supplied by the command.OPERATOR_ANSWERS— free text: intended production audience, known feature areas, constraints.
Phase 0: Probe
Confirm PROTOTYPE_ROOT exists (Bash: test -d). Probe for PROTOTYPE_ROOT/.bees (existence only, no bees invocation yet). Record the boolean — pass it to discovery workers so the bees-map shard is skipped gracefully when absent, never fabricated.
Phase 1: Discovery (harvest only spawns three-to-four shards; assess spawns one)
MODE=harvest: spawn pm-discovery in parallel, one per shard: routes-pages, data-models, integrations-deps-stack, plus bees-map only when the Phase 0 probe found .bees/. Pass each PROTOTYPE_ROOT and its SHARD; pass OPERATOR_ANSWERS-derived HINTS globs when the operator named known feature areas.
MODE=assess: spawn a single pm-discovery with SHARD=integrations-deps-stack. Skip the other shards — assessment needs the dependency/stack digest only.
Wait for every shard's report. Require the proof-of-loading quotes before accepting any report — reject and re-spawn a worker that omits them.
Merge shard reports into one INVENTORY text block, preserving each entry's confidence tag verbatim.
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.
- 1mo ago Changed ff65db78503d
- 2mo ago First seen · 98 lines · 54 tokens per session scan A 2d8349c8a390
pm-lead is an agent published in the GitHub repository vinnie357/claude-skills (27 stars, last pushed 14d ago), licensed MIT. It adds 54 tokens to every session and 1,375 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.
pm-lead compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| pm-leadvinnie357/claude-skills | Agent | 27 | 14d ago | MIT | A | 54 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 100k | today | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 79k | 2d ago | MIT | A | 33 | Claude Code |
| AVM Owner Triagegithub/awesome-copilot | Agent | 41k | today | MIT | A | 61 | Claude Code |
| Pimcore Expertgithub/awesome-copilot | Agent | 41k | today | MIT | A | 26 | Claude Code |
| Ultimate Transparent Thinking Beast Modegithub/awesome-copilot | Agent | 41k | today | MIT | A | 11 | Claude Code |
| WinForms Expertgithub/awesome-copilot | Agent | 41k | today | MIT | A | 19 | Claude Code |