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 skills add alielshenawy1/Ali-GTM-Brain-Skill --skill go-to-market-braingit clone --depth 1 https://github.com/alielshenawy1/Ali-GTM-Brain-SkillWrote 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/skills/alielshenawy1/ali-gtm-brain-skill/go-to-market-brain)<a href="https://agentmods.dev/skills/alielshenawy1/ali-gtm-brain-skill/go-to-market-brain"><img src="https://agentmods.dev/badge/skills/alielshenawy1/ali-gtm-brain-skill/go-to-market-brain/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/skills/alielshenawy1/ali-gtm-brain-skill/go-to-market-brain"><img src="https://agentmods.dev/badge/skills/alielshenawy1/ali-gtm-brain-skill/go-to-market-brain.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 | $0.00306 | $0.03150 |
| Opus 5 | $0.00153 | $0.01575 |
| Sonnet 5 | $0.00061 | $0.00630 |
| Haiku 4.5 | $0.00031 | $0.00315 |
Grade A, and why
go-to-market-brain 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 12d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Go-to-Market Brain
A Go-to-Market Brain is a plain-text repository that holds one company's entire go-to-market in a form an AI agent can load and execute against without re-deriving anything, and that a human operator can use as a command center for decisions. It is content and context, not application code.
It solves four problems at once. Strategy stops living in one person's head and in scattered files. Every asset inherits the same positioning and voice. Agents stop overclaiming, because what may be said is written down and checked. And the whole thing compounds: every lead conversation, customer signal, and periodic snapshot feeds back into the ledgers, so the brain gets sharper with use instead of going stale.
Route first
Three modes. Decide which one you are in before doing anything.
| The user has | Mode | Go to |
|---|---|---|
| Source material and no brain yet | BUILD | Phases 1 to 9 below |
| A brain, plus new input: a call note, an objection, a churn reason, a competitor move, a shipped feature, a metrics snapshot | UPDATE | reference/compounding.md |
| A brain, and wants an asset produced, reviewed, or shipped | OPERATE | reference/operating.md |
If a brain exists, never write customer-facing output without loading its entry file and control layer first. That is the point of the brain.
The three-layer architecture
Everything in the build serves one of three layers. Keep them distinct.
- Control layer. Small, authoritative, checked on every task: the entry files, the rules, the QA checklist. This is what governs output. Keep it short enough that loading it costs nothing.
- Reference layer. Large, authoritative, loaded on demand: the master context and one file per source artifact. This is the brain's memory.
- Execution layer. Templates, examples, prompts, finished pages. This is how work gets produced fast and on-voice.
Under all three sits the state layer (ops/ and snapshots/), which records what was decided, what language is approved, what has been heard from the market, and when each ledger was last reviewed. The state layer is what makes the brain compound.
What ships with it
51 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- adapters/brain/AGENTS.block.md 858 B
- adapters/brain/copilot-instructions.block.md 735 B
- adapters/brain/cursor.mdc 823 B
- adapters/brain/GEMINI.block.md 577 B
- adapters/brain/system-prompt.md 2.2 KB
- adapters/brain/windsurf.md 652 B
- adapters/README.md 2.3 KB
- adapters/skill/AGENTS.block.md 1.1 KB
- adapters/skill/codex-prompt.md 740 B
- adapters/skill/copilot-instructions.block.md 839 B
- adapters/skill/cursor.mdc 823 B
- adapters/skill/GEMINI.block.md 677 B
- adapters/skill/system-prompt.md 4.9 KB
- adapters/skill/windsurf.md 752 B
- assets/context/master-context.md 4.3 KB
- assets/entry/AGENTS.md 1.0 KB
- assets/entry/CLAUDE.md 1.5 KB
- assets/entry/llms.txt 2.5 KB
- assets/entry/README.md 2.7 KB
- assets/ops/asset-index.md 1.1 KB
- assets/ops/copy-bank.md 1.3 KB
- assets/ops/decisions.md 984 B
- assets/ops/QA-checklist.md 1.8 KB
- assets/ops/review-cadence.md 1.6 KB
- assets/ops/signal-log.md 2.2 KB
- assets/prompts/common-tasks.md 2.9 KB
- assets/rules/do-not-say.md 2.1 KB
- assets/rules/feature-status.md 1.0 KB
- assets/rules/glossary.md 778 B
- assets/rules/writing-rules.md 2.1 KB
- assets/snapshots/snapshot.md 1.8 KB
- assets/templates/ad-copy.md 529 B
- assets/templates/landing-page.md 1.5 KB
- assets/templates/long-form-script.md 1.5 KB
- assets/templates/newsletter.md 747 B
- assets/templates/one-pager.md 601 B
- assets/templates/README.md 1.1 KB
- assets/templates/repurposing.md 800 B
- assets/templates/seo-article.md 906 B
- assets/templates/short-form-script.md 655 B
- assets/templates/social-post.md 636 B
- reference/blueprint.md 11 KB
- reference/compounding.md 10 KB
- reference/extraction.md 8.1 KB
- reference/ledgers.md 8.6 KB
- reference/operating.md 3.2 KB
- reference/portability.md 5.3 KB
- reference/worked-example.md 11 KB
- scripts/audit_brain.py 12 KB runs code
- scripts/bundle_skill.py 7.1 KB runs code
- scripts/extract_sources.py 6.8 KB runs code
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.
- 12d ago First seen · 137 lines · 0 tokens per session scan A fc2be6eae450
go-to-market-brain is a skill published in the GitHub repository alielshenawy1/Ali-GTM-Brain-Skill (5 stars, last pushed 20d ago), licensed MIT. It adds 306 tokens to every session and 3,150 once invoked, about $0.0015 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…