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/build-model)<a href="https://agentmods.dev/commands/gtmagents/gtm-agents/build-model"><img src="https://agentmods.dev/badge/commands/gtmagents/gtm-agents/build-model/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/build-model"><img src="https://agentmods.dev/badge/commands/gtmagents/gtm-agents/build-model.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 | $0.00021 | $0.00691 |
| Opus 5 | $0.00010 | $0.00345 |
| Sonnet 5 | $0.00004 | $0.00138 |
| Haiku 4.5 | $0.00002 | $0.00069 |
Grade A, and why
build-model 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: build-model
Inputs
- use_case – name of metric or dashboard relying on the model.
- stack – modeling tool (dbt, LookML, Metrics Layer, SQL Runner, Python jobs).
- refresh – cadence (hourly, daily, weekly) or cron.
- dependencies – optional upstream tables or APIs.
- tests – optional list of validations to enforce.
GTM Agents Pattern & Plan Checklist
Mirrors GTM Agents orchestrator blueprint @puerto/plugins/orchestrator/README.md#112-325.
- Pattern selection: Modeling often runs pipeline (spec → blueprint → testing → deployment → docs). If testing + deployment prep can parallelize, log a diamond segment with merge gate.
- Plan schema: Save
.claude/plans/plan-<timestamp>.jsonwith objective, data lineage, task IDs, parallel groups, dependency matrix, error handling, and success metrics (freshness %, defect ceiling, SLA adherence). - Tool hooks: Reference
docs/gtm-essentials.mdstack—Serena for repo diffs/dbt patches, Context7 for platform docs, Sequential Thinking for review cadences, Playwright for UI validations tied to modeled data. - Guardrails: Default retry limit = 2 for failed tests/deployments; escalation path = Analytics Modeling Lead → Data Engineering Lead → RevOps.
- Review: Run
docs/usage-guide.md#orchestration-best-practices-puerto-paritybefore execution to confirm agents, dependencies, deliverables.
Workflow
- Spec Alignment – review event/tracking plan, KPI definitions, stakeholders.
- Model Blueprint – outline staging, intermediate, mart layers, join keys, surrogate IDs.
- Testing Strategy – define schema, freshness, unique, accepted value, and custom tests.
- Deployment Plan – schedule jobs, resource configs, backfill strategy, rollback steps.
- Documentation & Handoff – update dbt docs / catalog, change log, owner assignments.
Outputs
- Modeling spec (diagram, SQL pseudocode, dependencies).
- Test plan + configuration snippets.
- Deployment checklist with monitoring hooks and rollback instructions.
- Plan JSON entry stored/updated in
.claude/plansfor audit trail.
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 · 21 tokens per session scan A 8b15b7590c0b
build-model is a command published in the GitHub repository gtmagents/gtm-agents (397 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 21 tokens to every session and 691 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.