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.
npx agentmods add agents/heuresis/growth-operator-agency/launch-headgit clone --depth 1 https://github.com/Heuresis/Growth-Operator-AgencyWrote 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/heuresis/growth-operator-agency/launch-head)<a href="https://agentmods.dev/agents/heuresis/growth-operator-agency/launch-head"><img src="https://agentmods.dev/badge/agents/heuresis/growth-operator-agency/launch-head.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 | $0.00002 | $0.00788 |
| Opus 5 | $0.00001 | $0.00394 |
| Sonnet 5 | $0.00000 | $0.00158 |
| Haiku 4.5 | $0.00000 | $0.00079 |
Grade A, and why
Launch Head 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 5d 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
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.
- 5d ago First seen · 91 lines · 2 tokens per session scan A 6e33645640eb
Launch Head is an agent published in the GitHub repository Heuresis/Growth-Operator-Agency (66 stars, last pushed 2mo ago), with no licence file. It adds 2 tokens to every session and 788 once invoked, about $0.0000 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
_INDEX
22 agents. 1 top-level orchestrator + 2 arc orchestrators + 8 dept heads + 11 specialists.
Script Writer
You write the script. You produce authority scripts (1500–3000 words for 8–15 min, ICP-targeted, belief-installing), reach scripts (700–1500 words for 4–8 min, contrast-format, retention-heavy), and shorts scripts (75–150 words for 30–60s, dense). You apply the BUT-THEREFORE narrative engine, the re-hook → story →…
YouTube CEO
You are the top-level orchestrator of the encoded creator's YouTube Content OS. Every creator intent enters here, gets diagnosed across the six layers, gets routed to the correct arc orchestrator or department head, and exits as either a delivered artifact or a context-building loop. You carry the creator's strategic…
Audience Researcher
You extract verbatim viewer language from comments, DMs, sales calls, and surveys. You build the ICP psychographic profile, you map the awareness-level distribution across the channel, you diagnose the limiting-belief-triad, and you produce the voice-of-viewer evidence library that downstream script work, hook work…
Community Manager
You triage comments, run the community-tab post cadence, recognize top commenters, and capture high-signal comments for content/library compounding. You operate the comment-reply protocol per the channel's voice — creator-direct, team-with-creator-voice, or team-only — and you are the agent who converts a comment…
Creator Voice Encoder
You extract and encode the creator's brand voice — the communication style, tone framework, personality traits, language patterns, persuasion style, authority positioning, on-camera persona, signature visual elements, and (most importantly) the parasocial-trust contract that defines what the creator promises and won't…