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 deciqAI/knowledge-skills --skill cognitive-evolution-stagesgit clone --depth 1 https://github.com/deciqAI/knowledge-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/deciqai/knowledge-skills/cognitive-evolution-stages)<a href="https://agentmods.dev/skills/deciqai/knowledge-skills/cognitive-evolution-stages"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/cognitive-evolution-stages.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 5.1 | $0.00111 | $0.01992 |
| Opus 5 | $0.00056 | $0.00996 |
| Sonnet 5 | $0.00022 | $0.00398 |
| Haiku 4.5 | $0.00011 | $0.00199 |
Grade A, and why
cognitive-evolution-stages 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 8d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cognitive Evolution Stages
Overview
Most learning models treat acquisition as the final destination. This framework describes it as the starting line of a five-stage process (5阶段11层级) ending in evolution — where Stage 5 output restarts the cycle at a higher level. The diagnostic power is identifying where someone is stuck and what specific transition would unblock them. The most consequential stall is Stage 2→3: from imitation to genuine understanding with deliberate trade-off thinking.
Use AFTER [metacognition] to accurately self-locate. Use BEFORE [first-principles] — first-principles at Stage 2 produces confident error. Complements [nine-level-cognitive-tower]: this maps the PROCESS of development; that maps the STATE.
When to Use
- A developer, researcher, analyst, or creator produces sophisticated work but cannot generate genuinely novel solutions
- A team's "innovation" combines existing approaches without comparative trade-off evaluation
- A person has mastered Stage 2 and feels "something is missing" — cannot generate without a model to copy
- A mentee executes instructions perfectly but cannot diagnose what is wrong with their own approach
- When NOT to use: person lacks Stage 1 knowledge; block is motivational not developmental; Stage 2 imitation IS appropriate for a brand-new domain
Coaching Novices (Adaptive Front Door)
- Engine mode: user has a concrete case → run The Process directly.
- Coach mode: user is unfamiliar or has no concrete case → guide step by step.
In Coach mode, respond one step at a time. Each [WAIT] is a hard stop — output only that step's question, then stop.
- One-line what-it-is: "Five stages from knowing → copying → comparing trade-offs → creating new methods → self-correcting loop. Most people stall at Stage 2 because that's what gets rewarded."
- Check fit: "Pick one domain where you feel plateaued. What is it?"
- Elicit the real case: "Describe the last thing you produced there — did you start from an existing model or from the problem itself?"
[WAIT — do not advance until user responds]
- Map their work to the most honest stage. Ask: "What would Stage 3 look like — deliberately comparing 2-3 existing approaches and naming trade-offs before choosing?"
[WAIT — do not advance until user responds]
- Close: "If you reliably operated at Stage 3 in [domain], what would become possible that isn't now?"
[WAIT — do not advance until user responds]
What ships with it
2 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.
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.
- 8d ago First seen · 116 lines · 111 tokens per session scan A 2ce4ecd4327d
cognitive-evolution-stages is a skill published in the GitHub repository deciqAI/knowledge-skills (10 stars, last pushed 6d ago), licensed MIT. It adds 111 tokens to every session and 1,992 once invoked, about $0.0006 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
voice-builder
Ingests 5–20 of the user's writing samples and distils a reusable voice-profile.md — signature phrases, sentence-length distribution, opener/closer habits, punctuation quirks, vocabulary do/don't lists, tone sliders, and three calibration paragraphs with self-checks. Other skills load this file so every post sounds…
english-swe-daily
Daily English expression coach for intermediate software engineers. Use this skill whenever the user wants to improve their spoken or written English in a software engineering work context — especially for standups, Slack messages, 1:1s, meetings, giving feedback on code, asking for help, disagreeing politely, or…
agent-teacher
A teaching aid that explains technical ideas with a small runnable code example and a guided walkthrough. It is meant for learning how something works, not fixing existing code.
lecture-notes
Transform raw lecture content (transcript, plain text, or slides) into clean, structured, study-ready notes in Markdown. Use this skill whenever the user pastes lecture material — a transcript (with or without timestamps), course/lecture text, or slide content — and asks for notes, a summary, or help studying. Also…
master-debate
A skill for running an adversarial, multi-round debate between two Buddhist teachers. It is designed for questions where the teachers argue from different positions.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.