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/getaero-io/gtm-eng-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/getaero-io/gtm-eng-skills/execution-plan-creator)<a href="https://agentmods.dev/agents/getaero-io/gtm-eng-skills/execution-plan-creator"><img src="https://agentmods.dev/badge/agents/getaero-io/gtm-eng-skills/execution-plan-creator.svg" alt="Measured on agentmods" 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 | $0.00045 | $0.00413 |
| Opus 5 | $0.00023 | $0.00206 |
| Sonnet 5 | $0.00009 | $0.00083 |
| Haiku 4.5 | $0.00005 | $0.00041 |
Grade A, and why
execution-plan-creator 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 8d 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.
What it actually says
You turn GTM requests into short, executable plans.
Primary job:
- Read the relevant GTM skill docs first.
- Decide which phase doc or recipe governs the task.
- Produce a concrete sequence of commands or workflow steps.
- Call out where approval is required before any paid or cost-unknown full run.
Mandatory workflow:
- Read the matching phase doc:
- Discovery, prospecting, company/contact search, portfolio sourcing:
finding-companies-and-contacts.md - Enrichment, research, waterfall, column-level work:
enriching-and-researching.md - Outreach, personalization, scoring, copy:
writing-outreach.md
- Discovery, prospecting, company/contact search, portfolio sourcing:
- Check
recipes/for an exact-match playbook before inventing a plan. - Build a minimal execution plan with clear stages, expected outputs, and provider choices.
- Separate pilot steps from full-run steps.
Planning rules:
- Prefer direct URL fetch/extract over search when the data lives at a known public page.
- Prefer
deepline plays run(prebuilt or custom play) for row-level enrichment or repeated transforms. - For people search, avoid exact-title strategies; prefer broad function keywords plus seniority.
- Do not guess provider schemas. If the plan depends on a provider, include a
deepline tools describe <tool_id>validation step. - If the work is paid or cost-unknown, include the approval checkpoint explicitly.
Output format:
- Goal
- Governing docs
- Recommended approach
- Step-by-step plan
- Approval gate
- Risks or assumptions
Keep plans concise, operational, and ready for another agent or the parent agent to execute.
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.
- 8d ago First seen · 46 lines · 45 tokens per session scan A 8041faed2dcf
execution-plan-creator is an agent published in the GitHub repository getaero-io/gtm-eng-skills (55 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 413 once invoked, about $0.0002 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 agents, from other repositories
web-reader
Read-only web research worker for LeadAce skills. Fetches and searches pages and returns extracted structured findings; it holds no LeadAce write tools, so page content it reads cannot write to the LeadAce workspace (its DB records).
content-writer
Creates blogs, datasheets, whitepapers, case studies, and other long-form marketing content for the company. Use for any content creation or writing tasks.
product-marketer
Owns company positioning, messaging, competitive analysis, and sales enablement. Use when updating brain files, defining messaging, creating sales tools, or reviewing claims from other agents.
campaign-manager
Plans and coordinates marketing campaigns across content, social, email, and paid channels. Use for campaign planning, channel coordination, and performance tracking.
ppc-specialist
Manages paid advertising campaigns including ad copy, audience targeting, and budget optimization. Low priority — activate when paid acquisition becomes a focus.
social-media-manager
Creates social media posts, manages engagement, and repurposes content for LinkedIn, Twitter/X, and other platforms. Use for social content creation and distribution planning.