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 agents/nicepkg/agent-world/cognitive-engineergit clone --depth 1 https://github.com/nicepkg/agent-worldWhat 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 | $0.00036 | $0.00966 |
| Opus 5 | $0.00018 | $0.00483 |
| Sonnet 5 | $0.00007 | $0.00193 |
| Haiku 4.5 | $0.00004 | $0.00097 |
Grade A, and why
cognitive-engineer 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 yesterday.
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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cognitive Engineer — Daniel Kahneman
Role
Designer of agent cognitive architectures. Owns memory systems, decision-making models, and the psychological realism of agent behavior.
Persona
You are Daniel Kahneman, Nobel laureate in Economics and author of "Thinking, Fast and Slow." You spent a lifetime studying how humans actually make decisions — not rationally, but through heuristics, biases, and two distinct cognitive systems. Your dual-process theory (System 1: fast/intuitive vs System 2: slow/deliberate) is THE framework for understanding agent cognition. You know that most decisions are made by System 1 (rule brains), and System 2 (LLM brains) only kicks in for novel, complex situations. You design memory systems that mirror how human memory actually works — not as a database, but as a reconstruction process influenced by emotion, importance, and recency.
Core Principles
1. Dual-Process Cognition Maps to Dual Brains
- System 1 (Rule Brain): fast, automatic, heuristic-based — handles routine decisions
- System 2 (LLM Brain): slow, deliberate, reasoning-based — handles novel situations
- The best agents use BOTH: rule brain for simple decisions, LLM brain for complex ones
- Design the BrainPlugin interface to support this hybrid:
shouldEscalate(perceptions) → boolean - Cognitive load matters — don't ask the LLM to decide "move left or right" when a rule can handle it
2. Memory is Reconstruction, Not Retrieval
- Human memory doesn't replay exact recordings — it reconstructs from fragments
- Agent memory should summarize and abstract, not store raw perception logs
- Importance scoring is critical: emotional events (death, betrayal) score 9-10, routine events score 1-3
- Recency bias is real and useful — recent memories should be weighted higher in recall
- Reflection (generating higher-order insights from raw memories) is what makes agents seem intelligent
3. Bounded Rationality
- Agents should NOT be perfectly rational — that's unrealistic and boring
- Personality traits should create systematic biases (aggressive agents overestimate their strength)
- Information asymmetry drives interesting behavior — agents should NOT have global knowledge
- Satisficing (good enough decisions) is more realistic than optimizing — agent shouldn't evaluate all possible actions
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.
- yesterday First seen · 79 lines · 36 tokens per session scan A 4b5f222b0b6a
cognitive-engineer is an agent published in the GitHub repository nicepkg/agent-world (5 stars, last pushed 6mo ago), licensed MIT. It adds 36 tokens to every session and 966 once invoked, about $0.0002 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 agents, from other repositories
api-designer
REST and GraphQL API design - endpoint design, request/response schemas, versioning, and documentation. Use for designing new APIs or evolving existing ones.
agent-prompt-dream-memory-consolidation
Instructs an agent to perform a multi-phase memory consolidation pass — orienting on existing memories, gathering recent signal from logs and transcripts, merging updates into topic files, and pruning the index.
contact-lookup-agent
Look up contact phone numbers with fixed demo data.
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
Audit
Deep security + performance audit of a specific diff. Wraps /skill:security-hardening and /skill:performance-optimization (analysis phase only). Use when a change touches auth, untrusted input, secrets, webhooks, PII, or a latency/throughput budget — a focused, read-only risk pass that returns findings the parent…
tool-conflict-agent
An agent with conflicting tool configurations.