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 skills/fergius-engineering/instincts/critical-thinkingnpx skills add Fergius-Engineering/instincts --skill critical-thinkinggit clone --depth 1 https://github.com/Fergius-Engineering/instinctsWrote 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/fergius-engineering/instincts/critical-thinking)<a href="https://agentmods.dev/skills/fergius-engineering/instincts/critical-thinking"><img src="https://agentmods.dev/badge/skills/fergius-engineering/instincts/critical-thinking.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 | $0.00025 | $0.00443 |
| Opus 5 | $0.00013 | $0.00221 |
| Sonnet 5 | $0.00005 | $0.00089 |
| Haiku 4.5 | $0.00003 | $0.00044 |
Grade A, and why
critical-thinking 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 3d 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
The rule
A proposal that sounds reasonable can still be wrong, and the person proposing it, often the user sounding sure, can't always see the flaw. Before you build what was asked, run the idea through one concrete example. If the example breaks, stop and say so. Building first and finding the flaw later wastes everyone's time, and "they sounded confident" is not a reason to skip the check.
This sharpens superpowers' brainstorming: brainstorming explores what to build; this is the one-example probe it doesn't mandate.
Fires when
Someone proposes a rule, a filter, a UX behavior, or a piece of logic and you're about to implement it. Strongest when the proposer is sure and the idea sounds obviously fine.
How to apply
Pick one concrete case and walk the proposal through it, out loud. Use a case that stresses the edges, not the happy path. If the proposal produces a wrong or surprising result, name it plainly and explain the case before writing code. Offer the fix or ask the question. Don't implement first and find the flaw in testing.
Worked example
A user asks for a filter: "show only the highest-severity issue per file." Reasonable on its face. Run one example. A file has one critical bug and one minor one. Now the user switches to cleaning up minor issues and filters for them. That file vanishes from the minor filter, because its highest severity is critical. The filter hides the very things the user is trying to find. You caught a real regression with one example, before a line of code. The confident phrasing of the request didn't make it correct.
Red flags
| Thought | Reality |
|---|---|
| "They asked for it and they sound sure" | Confidence isn't correctness. Run the example. |
| "It's obviously fine, I'll just build it" | Obvious ideas fail on the case you didn't picture. |
| "I'll catch problems in testing" | Testing a flawed design just confirms the flaw works. |
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.
- 3d ago First seen · 31 lines · 25 tokens per session scan A ffdbbe9b6189
critical-thinking is a skill published in the GitHub repository Fergius-Engineering/instincts (2 stars, last pushed 9d ago), licensed MIT. It adds 25 tokens to every session and 443 once invoked, about $0.0001 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
loongsuite-pilot-insight
基于 LoongSuite Pilot / AI Coding Agent 日志生成事件洞察、组织洞察、数据质量、研发效能和 AI Native 使用类 SLS 报表时使用；包含 AI Coding 事件表语义，以及团队报表可选的部门维表、deptuser 组织关系、指标口径和公共 CTE，通常与 sls-dashboard-builder 一起使用。.
map-fast
Minimal workflow for small, low-risk changes — no planning, no learning.
codedrobe-theme
Create, inspect, convert, apply, replace, verify, troubleshoot, update, publish, or restore reversible CodeDrobe themes for supported Chromium/Electron AI desktop apps, including OpenAI Codex, Tencent WorkBuddy, QoderWork (CN/global), and TRAE SOLO (global/CN). Use when a user asks to turn an attached or local…
levelup-clarify
Review, accept, reject, or defer Context Directive Records (CDRs) discovered by levelup-init or proposed by levelup-specify. Interactive one-CDR-at-a-time workflow.
clio-webhooks
Receive and verify Clio (Clio Manage) webhooks. Use when setting up Clio webhook handlers, debugging X-Hook-Signature verification, completing the X-Hook-Secret handshake, or handling legal practice events like matter.created, contact.updated, activity.created, or bill events.
animate
Build a web animation: whether it should animate at all, the purpose, the tool, the properties, the easing curve, the duration, interruption and exit. Writes the CSS or Motion code for dropdowns, modals, toasts, tooltips, accordions, press feedback, stagger and scroll reveals. Use to animate something or make a…