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/fmind/agent-evolutions/run-agent-evolutionnpx skills add fmind/agent-evolutions --skill run-agent-evolutiongit clone --depth 1 https://github.com/fmind/agent-evolutionsWhat 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 | $0.00081 | $0.01750 |
| Opus 5 | $0.00041 | $0.00875 |
| Sonnet 5 | $0.00016 | $0.00350 |
| Haiku 4.5 | $0.00008 | $0.00175 |
Grade A, and why
run-agent-evolution 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
run-agent-evolution
Drive the genetic loop for <id-or-slug>. State is derived from evolution.yaml field presence — re-read between phases.
0. Dispatch
Resolve the argument:
- Pure integer → match the leading
<id>under.agents/evolutions/<id>-*/. - String → match a slug fragment; on multi-match pick the lowest
<id>and note in chat.
Read evolution.yaml (validated against evolution.schema.json). Branch:
- Directory missing →
"No evolution found for <arg>. Run /new-agent-evolution <title> to capture one."Stop. appliedset → terminal."Evolution <id> already applied (winner: <variant_id>)."Stop.winneralready set →"Winner already picked (v<n>). Run /apply-agent-evolution <id> to land it."Stop.- Otherwise → continue.
Each iteration is one generation — a batch of up to budget.parallel variants planned, executed, recorded together. The generation boundary is where the loop learns.
1. Resume sweep
On entry, reset any running variants without a result.json to pending and re-dispatch them. Variants with result.json already on disk → ingest immediately and mark evaluated.
2. Stop conditions (first match wins)
len(variants) >= budget.max_variants→ stop, pick winner.budget.max_minutesset and elapsed ≥ it → stop, pick winner.budget.plateau_generationsset and top score has not improved over the last N gens (need ≥ 2 full gens) → stop, pick winner.gen >= 2and zero eligible variants → abort; gate spec is likely broken.
3. Plan the next batch
Compute gen = max(variant.generation) + 1 (or 1). batch_size = min(parallel, max_variants - len(variants)).
Generation 1 — seed for diversity. For each seed, pick a distinct dimension to vary (algorithm, data structure, library, prompt style, control flow). Write a one-line falsifiable hypothesis and a 5–15 line approach concrete enough that a sub-agent can implement it without re-deriving. parents: [].
Generation 2+ — mutate, cross, explore. Read survivors (status evaluated, all gates passing, sorted by the composite score from §5). Mix per your judgment: mutations (parents: [v_n]), crossovers (parents: [v_a, v_b]), and one or two explores (fresh dimension; parents: []). When all prior variants failed gates, do not propagate them — diagnose and seed fresh.
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 · 98 lines · 81 tokens per session scan A 9e8005d65a01
run-agent-evolution is a skill published in the GitHub repository fmind/agent-evolutions (1 stars, last pushed 3mo ago), licensed MIT. It adds 81 tokens to every session and 1,750 once invoked, about $0.0004 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
gofer-documentation
Write or update customer-facing delivery documentation and generate its PublicAPI-capped lineage diagram. Use for Markdown, requirements, architecture, decisions, plans, validation evidence, or documentation graphs in a Gofer workspace.
eai
Start or continue the EAI delivery pipeline.
lever-new
Start a new lever — discuss the ask in chat, then capture intent (Goal, Success sketch, Context, Open questions) as §Brief. Hands off via /lever .
lever-status
Inspect or cancel levers. List all (no arg), detail one (TL;DR + criteria + per-criterion events timeline), or cancel one with cancel [ ]. Never advances the chain.
lever-init
Bootstrap a repo for agent-levers. Creates .agents/levers/, wires CLAUDE.md/GEMINI.md to import AGENTS.md, writes an AGENTS.md skeleton when missing. Hands off via /lever-new.
lever
Advance an existing lever. Reads lever.yaml.step and runs the chain (plan → do → check → act → done) autonomously until it pauses or finishes.