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/gtmagents/gtm-agentsWrote 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/gtmagents/gtm-agents/plan-plays)<a href="https://agentmods.dev/commands/gtmagents/gtm-agents/plan-plays"><img src="https://agentmods.dev/badge/commands/gtmagents/gtm-agents/plan-plays/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/gtmagents/gtm-agents/plan-plays"><img src="https://agentmods.dev/badge/commands/gtmagents/gtm-agents/plan-plays.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 | $0.00022 | $0.00739 |
| Opus 5 | $0.00011 | $0.00369 |
| Sonnet 5 | $0.00004 | $0.00148 |
| Haiku 4.5 | $0.00002 | $0.00074 |
Grade A, and why
plan-plays 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 9d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Command: plan-plays
Inputs
- tiering – map of tier counts (e.g.,
T1:10,T2:40). - window – program duration (e.g., 6w, quarter).
- objectives – pipeline, expansion, strategic meetings, adoption.
- channels – optional list (ads, email, direct mail, exec events, social).
- offers – optional predefined offers to include.
GTM Agents Pattern & Plan Checklist
Derived from GTM Agents orchestrator model @puerto/plugins/orchestrator/README.md#112-325.
- Pattern selection: Start with a diamond pattern (strategy intake → parallel pod planning → consolidation) and switch to pipeline when play development must stay sequential. Record the chosen pattern in the plan header.
- Plan schema: Every run saves
.claude/plans/plan-<timestamp>.jsonincluding objective, stages, parallel groups, agent assignments, context handoffs, error handling, and success criteria. - Tool hooks: Reference
docs/gtm-essentials.mdtools explicitly (Serena for CRM/MAP patches, Context7 for platform docs, Sequential Thinking for retros, Playwright for QA on assets/landing pages). - Guardrails: Define retry strategy (default 2 attempts) and escalation path (ABM Strategist → Sales Director) for any failed stage.
- Review: Before execution, run the checklist in
docs/usage-guide.md#orchestration-best-practices-puerto-parityto confirm agents, dependencies, and deliverables.
Workflow
- Strategy Alignment – confirm goals, budget, team capacity, channel constraints.
- Play Library Selection – choose plays per tier (executive experience, custom content, direct mail, workshops, ads).
- Timeline & Cadence – schedule waves of outreach, follow-up, and standups.
- Asset & Owner Mapping – identify required content, personalization, approvals, stakeholders.
- Measurement Plan – define KPIs per play (engagement, meetings, pipeline) and reporting cadence.
Outputs
- Playbook table (tier, play, channel, owner, CTA, assets, SLAs).
- Calendar/timeline highlighting waves, reviews, retros.
- Risk + dependency log (asset gaps, approval needs, data requirements).
- Plan JSON stored in
.claude/planswith version history (update if owners/scope change).
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.
- 9d ago First seen · 49 lines · 22 tokens per session scan A 23bc518d4469
plan-plays is a command published in the GitHub repository gtmagents/gtm-agents (397 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 22 tokens to every session and 739 once invoked, about $0.0001 per session on Opus 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.