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/miaoy0ushan/fp/self-evolvenpx skills add MiaoY0uShan/FP --skill self-evolvegit clone --depth 1 https://github.com/MiaoY0uShan/FPWrote 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/miaoy0ushan/fp/self-evolve)<a href="https://agentmods.dev/skills/miaoy0ushan/fp/self-evolve"><img src="https://agentmods.dev/badge/skills/miaoy0ushan/fp/self-evolve.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 | $0.00056 | $0.00807 |
| Opus 5 | $0.00028 | $0.00404 |
| Sonnet 5 | $0.00011 | $0.00161 |
| Haiku 4.5 | $0.00006 | $0.00081 |
Grade A, and why
fp-self-evolve 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 4d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FP Self-Evolution
Hermes-inspired closed learning loop. Three subsystems work together:
Memory Subsystem
Two files in the FP skill directory, loaded at session start:
../MEMORY.md (cross-project facts, max ~2200 chars)
- Environment facts (OS, tools, versions, paths)
- Project conventions (naming, layout, deploy patterns)
- Tool quirks ("pi on Windows needs
powershell.exenotpwsh") - Pitfalls ("akilecloud model IDs are full names like
gpt-5.6-sol, not display names")
../USER.md (user preferences, max ~1375 chars)
- Communication style
- Preferred tools and workflows
- Frequent patterns
- "Always / Never" rules
Skill Subsystem
When a task involves 5+ tool calls, an error overcome, a user correction, or a non-trivial workflow:
- Check if a relevant skill already exists in
../skills/or../ - If yes: patch the skill's Pitfalls section with fuzzy find-and-replace
- If no: create a new skill stub in
../skills/
Skill Creation Template
---
name: fp-<topic>
description: "<one-line summary of when to use>"
---
# <Title>
## Steps
1. ...
## Pitfalls
- <issue encountered>: <resolution>
Nudge Engine
Turn counter: After every ~10 user turns, run a silent reflection:
- Scan the last 10 turns for: errors resolved, new patterns, user corrections, tool discoveries
- Decide: anything worth saving?
- Yes → propose 1-2 concrete updates to MEMORY.md, USER.md, or a skill
- No → continue silently
Skill nudge: After any task with 5+ tool calls or an error overcome:
- Check if the workflow matches an existing skill
- If the skill missed a pitfall → patch it
- If no skill exists and this pattern has appeared in 2+ sessions → propose new skill
Evolution Pipeline
Compared to FP's existing adaptive-improvement (2-4 independent cases, full generalization gate), this is the fast track:
| Stage | Trigger | Action |
|---|---|---|
| Observation | Any non-trivial task | Auto-append to ../MEMORY.md if new |
| Shadow skill | Same pattern in 2 tasks | Create skill stub in ../skills/, mark metadata: { stage: "shadow" } |
| Active skill | Shadow succeeds 3 times | Promote description, remove shadow marker |
| Promoted | 4+ independent positive cases | Move through full generalization gate |
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.
- 4d ago First seen · 94 lines · 56 tokens per session scan A 60c28ac4bb6d
fp-self-evolve is a skill published in the GitHub repository MiaoY0uShan/FP (3 stars, last pushed 29d ago), licensed MIT. It adds 56 tokens to every session and 807 once invoked, about $0.0003 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
git-ai-search
Search and restore AI conversation context from git history.
brain-page
Operating manual for reading and writing a project's brain — every read and write goes through the bundled zero-dependency brain CLI; never hand-edit brain files. Read it before creating or modifying any page or root page.
brain-bootstrap
Seed a freshly-scaffolded brain with real project knowledge — on an existing (brownfield) project read the code, docs, and git log to draft the six root pages and capture key historical decisions; on a near-empty (greenfield) project interview the user. Every write goes through the brain CLI. Run it after brain-setup.
brain-ingest
The process for digesting a conversation, document, or research result, classifying it, and writing it down as brain content (a root-page update or a new/updated page) through the brain CLI.
immune
Hybrid adaptive memory: Cheatsheet (positive patterns pre-generation) and Immune (negative patterns post-generation) with Hot/Cold tiered auto-learning. Triggers on: "scan for errors", "immune scan", "check output quality", "antibody scan". NOT for PR review (use pr-review) or repo audits (use repo-sentinel).
ontology-sync
After a code change, sync the project's ontology vault — read what's already there, identify new capabilities / elements / domains introduced by the change, and write them back via the MCP server (or fall back to the CLI). Use this at the end of any task that introduces a new feature, refactors a module, or renames a…