os-evolve

A planning command for reviewing the last improvement cycle of a personal operating system and writing the next improvement plan.

In plain words
What is it for?
Use it to create one dated plan containing evidenced gaps and numbered prompts for the next round of improvements.
Why use it?
It turns evidence from audits, gaps, warnings, and the previous cycle into an ordered list of work without making those changes automatically.

Command for Claude Code

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 commands/arcassystems/founderos/os-evolve
Clone the repo
git clone --depth 1 https://github.com/ARCASSystems/FounderOS

Made for: Claude Code.

Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 311 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 $0.00061 $0.00311
Opus 5 $0.00030 $0.00156
Sonnet 5 $0.00012 $0.00062
Haiku 4.5 $0.00006 $0.00031

Measured 2d ago against content hash 7fed379bb6dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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.

.claude/commands/os-evolve.md · 24 lines

What it actually says

Founder OS evolve

Run the os-evolve skill at skills/os-evolve/SKILL.md end to end.

Procedure

  1. Read skills/os-evolve/SKILL.md.
  2. Pass $ARGUMENTS as the source file to evolve from. If empty, use the newest audit or plan in plans/. If plans/ is empty or missing, say so and build the gap list from flags, quarantine, and the last cycle only.
  3. Write exactly one file: plans/os-evolve-<today>.md. Create plans/ if it does not exist.
  4. Report the path, the counts, and the one prompt to run first.

Rules

  • Never execute the prompts this run just wrote. Planning and executing are separate sessions.
  • Never edit CLAUDE.md, rules/, or any User Layer file.
  • No gap without evidence. A hunch goes in the kill column.
  • No em dashes or en dashes. No banned words.
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 · 24 lines · 61 tokens per session scan A 7fed379bb6dd

Subscribe to this mod's changes

os-evolve is a command published in the GitHub repository ARCASSystems/FounderOS (5 stars, last pushed 18d ago), licensed MIT. It adds 61 tokens to every session and 311 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.