ai-dev-os-evolve

A review tool for improving an AI coding project's rules by studying recent commits, pull requests, and guideline-check results.

In plain words
What is it for?
Use it during monthly or quarterly reviews to analyze coding history, propose rule changes, show the difference, and apply updates after approval.
Why use it?
It reveals repeated mistakes and successful patterns, then turns them into proposed updates to the project's high-level principles.

Cursor rule

Install

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.

agentmods
npx agentmods add rules/yunbow/ai-dev-os-plugin-cursor/ai-dev-os-evolve
Clone the repo
git clone --depth 1 https://github.com/yunbow/ai-dev-os-plugin-cursor
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 242 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00045 $0.00242
Opus 5 $0.00023 $0.00121
Sonnet 5 $0.00009 $0.00048
Haiku 4.5 $0.00005 $0.00024

Measured 2d ago against content hash 9847c6f280a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai-dev-os-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 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.

rules/ai-dev-os-evolve.mdc · 32 lines

What it actually says

AI Dev OS Spiral Feedback (SECI Spiral)

Execution Flow

1. Analyze Recent N Commits/PRs

  • Aggregate past results from guideline checks
  • Identify frequently occurring violation patterns
  • Also detect patterns where "AI performed surprisingly well"

2. Abstract Patterns

Derive principles from individual cases:

  • "auth() forgotten 3 times" → Strengthen principle "Authentication should be explicit, not implicit"
  • "AI writes zod schemas accurately" → Confirm L3 rule is effective

3. Propose L1-L2 Updates

  • Candidates for new principles
  • Candidates for rewording existing principles
  • Values discovered at the philosophy level

4. Report + Present Diff

Ask "Would you like to apply the following updates?" and apply after approval.

Language

Respond in the same language as the project's .cursorrules file.

Changes

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.

  1. 2d ago First seen · 32 lines · 45 tokens per session scan A 9847c6f280a2

Subscribe to this mod's changes

ai-dev-os-evolve is a cursor rule published in the GitHub repository yunbow/ai-dev-os-plugin-cursor (2 stars, last pushed 5mo ago), licensed MIT. It adds 45 tokens to every session and 242 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.