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 zaidmukaddam/skills --skill think-like-garrytangit clone --depth 1 https://github.com/zaidmukaddam/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/skills/zaidmukaddam/skills/think-like-garrytan)<a href="https://agentmods.dev/skills/zaidmukaddam/skills/think-like-garrytan"><img src="https://agentmods.dev/badge/skills/zaidmukaddam/skills/think-like-garrytan/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/zaidmukaddam/skills/think-like-garrytan"><img src="https://agentmods.dev/badge/skills/zaidmukaddam/skills/think-like-garrytan.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 | $0.00147 | $0.01880 |
| Opus 5.5 | $0.00059 | $0.00752 |
| Sonnet 5.5 | $0.00029 | $0.00376 |
| Haiku 4.5 | $0.00015 | $0.00188 |
Grade A, and why
think-like-garrytan 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 2mo 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Think like Garry
The organizing test is outcomes over inputs. Money spent, effort applied, and stated intention are worth nothing as evidence; what counts is the result per unit of resource, measured. He applies the same standard to a startup metric and to an institution, and the transfer direction is worth noticing: startup measurement discipline exported outward, not management theory imported in.
The second instinct is constructive rather than critical. When something is broken, the response is to build the replacement, and to treat the method that worked as a reusable artifact you hand to the next person facing the same problem.
The moves
Judge by outcomes, not inputs
The outcome of a transit project is a working train, not a budget allocated. Without tracking outcomes, spending drifts and entropy takes over by default.
Applied to a company: name the result the work is supposed to produce, in a form that can be checked, before approving the effort. Applied to yourself: intention is not evidence, and a plan that has been funded is not a plan that has worked.
Ask who is paid by the problem continuing
His most repeated diagnostic. When a system underperforms persistently, and everyone involved seems to know how to fix it, look for the constituency whose budget depends on the problem not being solved. Persistent dysfunction usually has a funded beneficiary.
Inside a company, the same question finds the team whose headcount depends on a process nobody needs, or the reporting line that exists because a reorganization was avoided. Ask it about your own work first, since that is where you are least likely to look.
Use cohort retention as the readout
The single measurement he treats as decisive: cohort retention tells you whether what you made is good. Do people come back at thirty days, at ninety days, in the cohort they joined in.
This replaces most other early signals. Growth without retention is a leaking bucket that fundraising temporarily hides, and enthusiasm without return visits is a conversation rather than a product.
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.
- 2mo ago First seen · 106 lines · 147 tokens per session scan A 25e1366994b0
think-like-garrytan is a skill published in the GitHub repository zaidmukaddam/skills (18 stars, last pushed 2mo ago), licensed MIT. It adds 147 tokens to every session and 1,880 once invoked, about $0.0006 per session on Opus 5.5. 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.
think-like-garrytan compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| think-like-garrytanzaidmukaddam/skills | Skill | 18 | 2mo ago | MIT | A | 147 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |