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 skills add SethGammon/Citadel --skill evolvegit clone --depth 1 https://github.com/SethGammon/CitadelWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/sethgammon/citadel/evolve)<a href="https://agentmods.dev/skills/sethgammon/citadel/evolve"><img src="https://agentmods.dev/badge/skills/sethgammon/citadel/evolve/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sethgammon/citadel/evolve"><img src="https://agentmods.dev/badge/skills/sethgammon/citadel/evolve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00060 | $0.03539 |
| Opus 5.5 | $0.00024 | $0.01416 |
| Sonnet 5.5 | $0.00012 | $0.00708 |
| Haiku 4.5 | $0.00006 | $0.00354 |
Grade A, and why
evolve scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/evolve — Improvement Director
Orientation
Use when: You want sustained autonomous quality advancement — the director forms hypotheses, scouts before attacking, and builds a belief model that compounds across cycles. Runs until a natural ceiling, budget exhaustion, or you say stop.
Don't use when: You want a single scored loop (/improve), a known axis
attacked directly (/improve --axis), or a one-time audit (/improve --score-only).
Key difference from /improve: /improve follows the rubric mechanically.
/evolve asks why scores are where they are, validates those theories before
spending fleet budget, and extracts cross-skill patterns that propagate to skills
never directly attacked.
Invocation
/evolve {target} # run until ceiling, velocity drop, or budget
/evolve {target} --n={N} # exactly N director cycles then stop
/evolve {target} --budget=${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.
- 1mo ago First seen · 304 lines · 60 tokens per session scan A c9d55a85bcd6
evolve is a skill published in the GitHub repository SethGammon/Citadel (924 stars, last pushed today), licensed MIT. It adds 60 tokens to every session and 3,539 once invoked, about $0.0002 per session on Opus 5.5. 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
compose-org
Run a task as an evolved multi-agent ORG using the installed liquid-org framework — where YOU (the running Claude) embody the org: you ask liquid-org which proven team topology + specialist personas to use (retrieved from its evolved pool, or assembled fresh), then dispatch ONE SUBAGENT PER TALENT to play each role…
liquid-rank
Rank the available skills by RELEVANCE to the current task, on demand, using liquid-org's read-only hermes skill ranker. This is an EXPLICIT, OPT-IN selector you invoke WHEN you want help choosing the most relevant skill for what you're doing — it is NOT default, automatic skill selection, and it does NOT decide for…
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.
audit-project
Run an iterative multi-agent code audit until critical and high findings are resolved. Use when the user says "audit my code", "find all the bugs", "deep code audit", "iterative review", or "review until clean".
prototype
Use when asked to prototype one design question through a cheap logic or UI experiment, including button-driven state-model checks. Not for polished artifacts: use polished-web-prototype.
contexts
Use when the user says "get context on X", "how does X work", or wants architectural orientation before coding.