agentmods.dev

DQIII8: Command for Claude Code

.claude/commands/evolve.md

evolve is a command for Claude Code from senda-labs/DQIII8. It costs 41 tokens per session (549 once invoked), scanned A, original, MIT.

An unimplemented command intended to group frequently used or trusted instincts—small learned rules—into draft skills for review.

In plain words
What is it for?
It is intended for clustering instincts by keyword, creating skill drafts, and recording them for review and approval.
Why use it?
It would turn repeated agent lessons into reusable instructions, while keeping them pending until a user approves them. Currently, it cannot run because its implementation file is missing.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is senda-labs/DQIII8's own configuration. It tells Claude Code how to work on DQIII8 itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything DQIII8 configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 /root/dqiii8/bin/evolve.py "$@".

Part of the dqiii8 plugin — 22 skills, 14 commands, 17 agents shipped together

not rated 11 17d ago A scan 41 tokens original MIT
View the source file senda-labs/DQIII8
Reuse

Borrowing it

Nothing to install: this file belongs to senda-labs/DQIII8. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/senda-labs/DQIII8/main/.claude/commands/evolve.md
Clone the repo
git clone --depth 1 https://github.com/senda-labs/DQIII8

Made for: Claude Code.

Or install dqiii8, the plugin that ships this one along with the rest of its 22 skills, 14 commands, 17 agents.

Wrote 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.

agentmods badge for evolve

README.md
[![agentmods](https://agentmods.dev/badge/commands/senda-labs/dqiii8/evolve.svg)](https://agentmods.dev/commands/senda-labs/dqiii8/evolve)
Your own site
<a href="https://agentmods.dev/commands/senda-labs/dqiii8/evolve"><img src="https://agentmods.dev/badge/commands/senda-labs/dqiii8/evolve.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 549 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 5.1 $0.00041 $0.00549
Opus 5 $0.00020 $0.00275
Sonnet 5 $0.00008 $0.00110
Haiku 4.5 $0.00004 $0.00055

Measured 6d ago against content hash 2e83b1ef0596, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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/evolve.md · 55 lines

What it actually says

DESHABILITADO: bin/evolve.py no existe. Este comando fallará si se invoca. Documentado tal cual (no implementado), no eliminado — ver TODO abajo.

/evolve — Convertir Instincts en Skills

Lee instincts con alta confianza o alta frecuencia de aplicacion de dqiii8.db, los agrupa por keyword raiz, y genera skill drafts para clusters con 3+ instincts.

Uso

/evolve
/evolve --min-confidence 0.5
/evolve --min-applied 10
/evolve --min-cluster 2
/evolve --dry-run

Que hace

  1. Lee instincts con confidence >= 0.7 OR times_applied >= 5 (ajustable)
  2. Agrupa por primer segmento del keyword (ssim-hacking → raiz ssim)
  3. Para clusters con 3+ instincts: escribe skills-registry/custom/evolved/[raiz].md
  4. Registra en skills-registry/INDEX.md con status PENDIENTE_REVISION

Implementacion

python3 /root/dqiii8/bin/evolve.py "$@"

Flujo de aprobacion

  1. Revisar el draft en skills-registry/custom/evolved/[raiz].md
  2. Editar las secciones "Reglas consolidadas" y "Anti-patrones"
  3. Cambiar status en INDEX.md a ✅ APROBADA
  4. Mover de custom/evolved/ a custom/[nombre]/SKILL.md

Notas DQIII8

  • Threshold por defecto: confidence >= 0.7 OR times_applied >= 5
  • Las skills en custom/evolved/ NO se cargan en sesion — requieren aprobacion manual
  • El comando es idempotente: re-ejecutar no sobreescribe skills existentes en INDEX
  • Las skills evolucionadas son mas precisas que las importadas de ECC/ruflo porque provienen de comportamiento real del sistema (5.687+ acciones acumuladas)
  • Complementa P3c (Intelligence Loop): P3c ajusta confidence, /evolve la convierte en skill
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. 6d ago First seen · 55 lines · 41 tokens per session scan A 2e83b1ef0596

Subscribe to this mod's changes

evolve is a command published in the GitHub repository senda-labs/DQIII8 (11 stars, last pushed 17d ago), licensed MIT. It adds 41 tokens to every session and 549 once invoked, about $0.0002 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.

Building agentsai-agentai-automationai-orchestrationai-routingclaudeclaude-code
Related

Other commands, from other repositories

evolve

Trigger harness evolution: analyze evaluation logs, propose changes, apply to experimental pool.

SeongwoongCho/adaptive-harness · 15 tokens

run

Run a task through the adaptive-harness pipeline explicitly.

SeongwoongCho/adaptive-harness · 10 tokens

status

Show adaptive-harness pool state, performance stats, and evolution history.

SeongwoongCho/adaptive-harness · 13 tokens

eval

Manually evaluate the last task result or a specific change.

SeongwoongCho/adaptive-harness · 11 tokens

prd-score

Score an existing PRD against the 100-point AI-optimization framework.

nyldn/claude-octopus · 14 tokens

pr-enhance

Command "pr-enhance" from shyftlabs/continuum, covering pr-enhance, usage, options, examples and enhance pr.

shyftlabs/continuum · 0 tokens