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 hamza-ali-shahjahan/hamzaish --skill devils-advocategit clone --depth 1 https://github.com/hamza-ali-shahjahan/hamzaishWrote 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/hamza-ali-shahjahan/hamzaish/devils-advocate)<a href="https://agentmods.dev/skills/hamza-ali-shahjahan/hamzaish/devils-advocate"><img src="https://agentmods.dev/badge/skills/hamza-ali-shahjahan/hamzaish/devils-advocate/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/hamza-ali-shahjahan/hamzaish/devils-advocate"><img src="https://agentmods.dev/badge/skills/hamza-ali-shahjahan/hamzaish/devils-advocate.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 | $0.00038 | $0.00553 |
| Opus 5.5 | $0.00015 | $0.00221 |
| Sonnet 5.5 | $0.00008 | $0.00111 |
| Haiku 4.5 | $0.00004 | $0.00055 |
Grade A, and why
devils-advocate 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 1mo 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Devil's Advocate
When you activate
- User asks: "stress-test this", "argue against this", "what could go wrong with X?"
- Automatically: whenever a new idea is added or validation is being considered "done"
What you produce
## The kill case
The strongest argument this fails: <one paragraph>
## Hidden assumptions
1. <assumption> — true if <condition>; we don't yet have evidence
2. <assumption> — ...
3. <assumption> — ...
## Disconfirming evidence to look for
- <specific signal that would prove the idea wrong>
- <another signal>
- <another signal>
## Failed analogs
- <prior company / product that tried this and why it failed>
- <another>
## The version that survives
If the above is right and we kept doing this, the version that might actually work is: <one sentence>
## Verdict
- KILL — the case against is strong enough to stop now
- PIVOT — the original is wrong but a near-neighbor might work
- PROCEED with eyes open — case isn't fatal, but track these assumptions
Protocol
- Read the user's idea statement (and
products/<name>/scope.md+prd.mdif it's for an existing product). - Genuinely try to kill it. No throat-clearing about "playing devil's advocate" — just do it.
- Run a quick web check for failed analogs if the idea is in a known vertical (use WebSearch).
- Force the verdict. KILL/PIVOT/PROCEED. Don't hedge.
What "strongest argument" means
- Cite real prior attempts when possible.
- Attack the value prop, not the execution.
- Find structural reasons (market dynamics, switching costs, distribution moats), not surface ones ("the UI could be better").
Sources
knowledge-base/idea-stage/mom-test.mdknowledge-base/founders-wisdom/paul-graham-essays.mdknowledge-base/ai-native-2026/founders-playbook-distilled.md(re: loss of objectivity)
What you don't do
- Don't soften. The user explicitly asked for the kill case. Soft devil's advocacy is useless.
- Don't recommend just because Hamza is excited. Excitement is a known bias (per the playbook).
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.
- 1mo ago First seen · 59 lines · 38 tokens per session scan A 7fe780d69622
devils-advocate is a skill published in the GitHub repository hamza-ali-shahjahan/hamzaish (11 stars, last pushed 18d ago), licensed MIT. It adds 38 tokens to every session and 553 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
gingiris-launch
A multilingual launch guide for releasing an AI product on Product Hunt and other marketing channels. Product Hunt is a website where new technology products are presented to an audience and ranked through community attention.
payments-polar
A reference for adding Polar payments to a product, covering Polar as the seller of record, payment types, checkout, webhooks, and customer access.
stack-reference
A setup guide for the AI Garage technology stack, covering tools for code hosting, web apps, databases, user accounts, analytics, email, and payments.
unit-economics
A guide to measuring how people discover, use, and pay for a product. It explains metrics such as CAC, LTV, retention, cohorts, and UTM tracking.
traffic-channels
A reference guide to 12 traffic channels, such as search engines, social networks, advertising, and developer communities. It compares who each channel reaches, how quickly it can work, and the usual time or budget involved.
make-playbook
An indie maker playbook inspired by Pieter Levels' (@levelsio) book "MAKE: The Indie Maker Blueprint" — idea validation, fast/DIY building, launching, organic growth, monetization, automation, and exits for bootstrapped apps. Use when the user is starting a new app idea, deciding what to build or build next, prepping…