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 rules/javanc/homunculus/evolution-systemgit clone --depth 1 https://github.com/JavanC/HomunculusWhat 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 | $0.00625 | $0.00625 |
| Opus 5 | $0.00313 | $0.00313 |
| Sonnet 5 | $0.00125 | $0.00125 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
evolution-system 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 2d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evolution System (Homunculus)
Evolution Artifacts (all in homunculus/evolved/)
| Artifact | Location | Evolution Method |
|---|---|---|
| Skills | evolved/skills/ |
Instinct aggregation (hm-night), eval→improve loop |
| Agents | evolved/agents/ |
Extract repetitive main-thread patterns into subagents |
| Evals | evolved/evals/ |
Accompany each skill, scenario-based testing |
Evolution Flow
Observe (observations.jsonl) → Three-layer extraction:
├── Instincts (behavioral patterns, confidence > 0.7, Write Gate)
│ ↓ supersedes check → auto-archive replaced instincts
│ ↓ run evolution → route to best mechanism (hook/rule/skill/script/agent/...)
│ ↓ if skill → eval → improve loop → 100% pass
├── Memory suggestions → reports/memory-suggestions.jsonl (user reviews)
└── Research topics → reports/research-queue.jsonl (nightly agent picks up)
Triggers (say these to run evolution workflows)
| User says | Action |
|---|---|
| "run evolution" / "nightly cycle" / "hm-night" | Follow homunculus/commands/hm-night.md |
| "define goals" / "goal tree" / "hm-goal" | Follow homunculus/commands/hm-goal.md |
| "system status" / "hm-status" | Follow homunculus/commands/hm-status.md |
| "evolve skill" / "aggregate instincts" | Follow homunculus/commands/evolve.md |
| "eval skill" / "test skill" | Follow homunculus/commands/eval-skill.md |
| "improve skill" | Follow homunculus/commands/improve-skill.md |
Automatic Maintenance
- Three-layer extraction: instincts + memory + research from sessions
- Semantic dedup: new instincts auto-archive superseded ones
- Smart pruning: reference frequency + 3-tier skill coverage + confidence decay (14-day grace)
- Skill eval → improve pipeline
Key Paths
architecture.yaml— goal tree (read this to understand project goals)evolution-config.yaml— tier/schedule/budget confighomunculus/instincts/personal/— auto-extracted behavioral patternshomunculus/evolved/skills/— tested, versioned knowledgehomunculus/observations.jsonl— tool usage datahomunculus/commands/— detailed workflow instructions
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.
- 2d ago First seen · 53 lines · 625 tokens per session scan A 4f1a428aa93b
evolution-system is a cursor rule published in the GitHub repository JavanC/Homunculus (15 stars, last pushed 3mo ago), licensed MIT. It adds 625 tokens to every session, about $0.0031 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 2026-08-30.
Other cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
python_lib
Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.
specs
This directory contains product and tech specs for Streamlit features.