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/Infrasity-Labs/dev-gtm-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/commands/infrasity-labs/dev-gtm-claude-skills/pm)<a href="https://agentmods.dev/commands/infrasity-labs/dev-gtm-claude-skills/pm"><img src="https://agentmods.dev/badge/commands/infrasity-labs/dev-gtm-claude-skills/pm/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/commands/infrasity-labs/dev-gtm-claude-skills/pm"><img src="https://agentmods.dev/badge/commands/infrasity-labs/dev-gtm-claude-skills/pm.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 | $0.00590 |
| Opus 5 | $0.00000 | $0.00295 |
| Sonnet 5 | $0.00000 | $0.00118 |
| Haiku 4.5 | $0.00000 | $0.00059 |
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 11d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parse the arguments: $ARGUMENTS
The first word is the subcommand. Everything after it is the input.
Route to the correct skill based on the subcommand:
Strategy & planning
strategy <product or context>— Invoke theproduct-strategistskill. Pass the product or context to drive vision, OKR cascades, quarterly planning, roadmaps, and team scaling.prd <feature or notes>— Invoke theprd-developmentskill. Pass the feature or discovery notes to build a structured, engineering-ready PRD.prioritize <context>— Invoke theprioritization-advisorskill. Pass the context to choose the right prioritization framework (RICE, ICE, value/effort, etc.).
Execution & agile
backlog <story or sprint context>— Invoke theagile-product-ownerskill. Pass the context to write user stories, define acceptance criteria, plan sprints, and track velocity.story-map <product or journey>— Invoke theuser-story-mappingskill. Pass the product or user journey to build a user story map (activities, steps, tasks, release slices).
Growth & toolkit
growth <growth constraint>— Invoke theorganic-growth-advisorskill. Pass the growth constraint to diagnose which organic growth path to pursue (segments, geographies, channels, or products).toolkit <PM task>— Invoke theproduct-manager-toolkitskill. Pass the PM task for RICE prioritization, customer interview analysis, PRD templates, discovery frameworks, and go-to-market strategy.
Meta
create-skill <idea or content>— Invoke thepm-skill-creatorskill. Pass the raw idea or content to design a new PM skill through guided conversation.
If no subcommand is given or the subcommand is unrecognised, display this help:
Strategy & planning:
/pm strategy <product or context> Drive vision, OKRs, roadmaps & team scaling
/pm prd <feature or notes> Build a structured, engineering-ready PRD
/pm prioritize <context> Pick the right prioritization framework
Execution & agile:
/pm backlog <story or sprint context> User stories, acceptance criteria, sprints
/pm story-map <product or journey> Build a user story map of the journey
Growth & toolkit:
/pm growth <growth constraint> Diagnose the organic growth path to pursue
/pm toolkit <PM task> RICE, interviews, discovery, PRD templates, GTM
Meta:
/pm create-skill <idea or content> Design a new PM skill through guided conversation
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.
- 11d ago First seen · 46 lines · 0 tokens per session scan A 2890bcef97b2
pm is a command published in the GitHub repository Infrasity-Labs/dev-gtm-claude-skills (124 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 590 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 2026-08-30.
Other commands, from other repositories
tasks
Use the Skill tool to run agentii:tasks on this workspace (spec 046 kit skill — read its SKILL.md for the full methodology, gates and invocation).
project-health
Audit and manage project configuration — permissions, context, docs.
status
Command "status" from ngocsangyem/MeowKit, covering /mk:status — delivery status report, usage, behavior, execution steps and skip conditions.
memory-sprint
Show current sprint state from StudioMeyer Memory.
new-client
Scaffold a new client project — folders, client.yml, CLAUDE.md — then interview for the essentials and fill the profile.
triage
Promote ideas from Ideas.md into Epics or User Stories in the Epic backlog (dedup, typed ID, voice).