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/sethgammon/citadel/evolvenpx skills add SethGammon/Citadel --skill evolvegit clone --depth 1 https://github.com/SethGammon/CitadelWhat 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 | $0.00060 | $0.03539 |
| Opus 5 | $0.00030 | $0.01769 |
| Sonnet 5 | $0.00012 | $0.00708 |
| Haiku 4.5 | $0.00006 | $0.00354 |
Grade A, and why
evolve scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/evolve — Improvement Director
Orientation
Use when: You want sustained autonomous quality advancement — the director forms hypotheses, scouts before attacking, and builds a belief model that compounds across cycles. Runs until a natural ceiling, budget exhaustion, or you say stop.
Don't use when: You want a single scored loop (/improve), a known axis
attacked directly (/improve --axis), or a one-time audit (/improve --score-only).
Key difference from /improve: /improve follows the rubric mechanically.
/evolve asks why scores are where they are, validates those theories before
spending fleet budget, and extracts cross-skill patterns that propagate to skills
never directly attacked.
Invocation
/evolve {target} # run until ceiling, velocity drop, or budget
/evolve {target} --n={N} # exactly N director cycles then stop
/evolve {target} --budget=${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 |
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.
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.
- 2d ago First seen · 304 lines · 60 tokens per session scan A c9d55a85bcd6
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.
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.
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.
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…
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…
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.
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…