evolve

A research-led improvement director that studies why a project's scores are low, tests possible causes, and sends targeted improvement work to several parallel reviewers.

In plain words
What is it for?
Use it for sustained, multi-cycle improvement of a target, or to inspect its status, continue previous work, set a budget, or focus on one quality area.
Why use it?
It helps guide repeated quality improvements when the underlying problems are unclear. It keeps a lasting record of what seems to work and can continue from an earlier run.

Skill for Claude CodeCodex

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 skills/sethgammon/citadel/evolve
Any agent
npx skills add SethGammon/Citadel --skill evolve
Clone the repo
git clone --depth 1 https://github.com/SethGammon/Citadel

Made for: Claude Code, Codex.

Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,539 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 $0.00060 $0.03539
Opus 5 $0.00030 $0.01769
Sonnet 5 $0.00012 $0.00708
Haiku 4.5 $0.00006 $0.00354

Measured 2d ago against content hash c9d55a85bcd6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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.

skills/evolve/SKILL.md · 304 lines

How it starts

The opening of the file, as written. The whole thing — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/evolve — Improvement Director

Orientation

Use when: You want sustained autonomous quality advancement — the director forms hypotheses, scouts before attacking, and builds a belief model that compounds across cycles. Runs until a natural ceiling, budget exhaustion, or you say stop.

Don't use when: You want a single scored loop (/improve), a known axis attacked directly (/improve --axis), or a one-time audit (/improve --score-only).

Key difference from /improve: /improve follows the rubric mechanically. /evolve asks why scores are where they are, validates those theories before spending fleet budget, and extracts cross-skill patterns that propagate to skills never directly attacked.

Invocation

/evolve {target}                  # run until ceiling, velocity drop, or budget
/evolve {target} --n={N}          # exactly N director cycles then stop
/evolve {target} --budget=${X}    # run until cumulative spend reaches $X
/evolve {target} --continue       # resume from saved director state
/evolve {target} --status         # show belief model, velocity, spend — no attack
/evolve {target} --axis={name}    # focus director on one axis (scout + attack only)

target maps to .planning/rubrics/{target}.md. If no rubric exists, run /improve {target} Phase 0 first — /evolve requires an approved rubric and will not auto-generate one.

Campaign Artifacts

All findings are externalized incrementally — written after every phase, not only at cycle end. A crashed or compacted session resumes with full context.

Artifact Path Contents
Director state .planning/evolve/{target}/director-state.json cycle count, spend, velocity history, current phase, halt status
Belief model .planning/evolve/{target}/belief-model.jsonl one record per (axis, skill) per cycle: score, hypothesis, evidence, confidence
Experiment log .planning/evolve/{target}/experiment-log.jsonl every experiment: hypothesis → prediction → actual delta → mechanism confirmed
Pattern library .planning/evolve/{target}/pattern-library.md transferable patterns: what change to what axis class caused what delta in which skills
Cycle digest .planning/evolve/{target}/cycle-{n}-digest.md human-readable per-cycle summary for review
Global patterns .planning/research/patterns.md cross-target patterns written outside campaign scope; available to future sessions and other targets
Knowledge wiki .planning/wiki/ compiled wiki pages from /learn; integrates evolve discoveries across sessions

Read the full file on GitHub · 304 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 304 lines · 60 tokens per session scan A c9d55a85bcd6

Subscribe to this mod's changes

evolve is a skill published in the GitHub repository SethGammon/Citadel (914 stars, last pushed 5d ago), licensed MIT. It adds 60 tokens to every session and 3,539 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 2026-08-30.

Related

Other skills, from other repositories

debrief

This skill should be used when the user asks to "debrief", "record what happened", "session summary", "write a debrief", or wants to capture session activity (commits, task state changes, decisions, issues) into a structured record for the next session.

spacedock-dev/spacedock · 59 tokens

refit

This skill should be used when the user asks to "refit a workflow", "upgrade a workflow", "update workflow scaffolding", or wants to bring an existing workflow's scaffolding files up to date with the current Spacedock version.

spacedock-dev/spacedock · 52 tokens

fo-dispatch-recovery

Claude dispatch failure recovery — Break-Glass Manual Dispatch (the manual Agent() template) and Context Budget Failure/Dead Ensign Handling (the budget-unavailable stderr conditions, the recovery clause, dead-ensign bookkeeping). Read ONLY at its resident triggers inside claude-fo-dispatch.md — a non-zero or…

spacedock-dev/spacedock · 137 tokens

fo-status-viewer

First-officer status query/mutate/display surface — the status command flag docs, --set field docs, canonical captain-facing invocations, the Captain-Facing State Display rendering, and the GitHub-issue-filing approval gate. Invoke at the first ad-hoc status question, --set mutation, --next-id/--resolve lookup, or…

spacedock-dev/spacedock · 87 tokens

present-gate

First-officer gate-presentation rendering — the captain-facing gate-review template and assembly rules, including workflow-owned finding labels. Invoke at the gate point after the FO has decided a stage must be presented.

spacedock-dev/spacedock · 44 tokens

agent-workflow-playbook

AI Agent Workflow & Skill Architecture Guide — turn expert work into measurable, reusable agent systems. Covers workflow discovery, skill decomposition, harness design, evaluation, human escalation, observability, cost control, and multi-agent orchestration. Includes a measured marketing-delivery case: 15 people × 3–4…

Gingiris-1031/gingiris-skills · 83 tokens