evolve

A governed process for improving an AI agent from recorded evidence through a proposed change, human approval, and the normal development workflow.

In plain words
What is it for?
It handles feedback and experience records, candidate changes, recommendations, approvals, archived handoffs, and controlled evolution modes.
Why use it?
It separates evidence from speculation and ensures self-improvement proposals still wait for human approval before they enter the work queue or are merged.

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/our-ark/enoch/evolve
Any agent
npx skills add our-ark/enoch --skill evolve
Clone the repo
git clone --depth 1 https://github.com/our-ark/enoch

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,832 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 $0.00000 $0.01832
Opus 5 $0.00000 $0.00916
Sonnet 5 $0.00000 $0.00366
Haiku 4.5 $0.00000 $0.00183

Measured 3d ago against content hash 04d576331fee, 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 3d 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.

src/enoch/skills/evolve/SKILL.md · 205 lines

How it starts

The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evolve

Purpose

Use this skill when Enoch should inspect, propose, or govern a small self-evolution step. Evolution is an evidence-to-change pipeline, not a generic task runner:

records -> evidence -> candidate -> recommendation -> human approval
        -> archived handoff -> normal task and review lifecycle

Backlog entries are ordinary deferred work and are never evolution evidence by themselves.

Modes

  • disabled: do not scan, synthesize, or propose self-evolution.
  • co-evolve: notice and recommend changes, but wait for human approval.
  • auto-evolve: schedule the same semantic proposal flow, but still wait for human approval before queueing, removing, or merging anything.

The default is co-evolve. The current theme guides synthesis, brainstorming, curation, and deterministic fallback ranking; it is context, not an evidence source.

Evidence pathways

Feedback and experience are two-stage pathways. They first create durable evidence, then a separate reasoning pass may turn unlinked evidence into candidate changes.

Feedback

The feedback scanner reads unprocessed conversation turns in configurable batches, defaulting to 20 user messages. Each record contains the exact user message and Enoch reply, plus a stable conversation:<id> reference. Credential values are redacted before the records leave storage.

The scanner runs in a fresh stateless runtime invocation. It receives no normal conversation session and returns a strict JSON array of zero or more observations. Simple words, phrases, and regular expressions do not classify feedback.

Experience

The experience scanner reads configurable batches of distinct changed task IDs, defaulting to 20. Each record contains that task's complete ordered event history from .enoch/artifacts/task_events.jsonl, not merely the last event.

The scan cursor records the latest event ID for each task. A later lifecycle event makes that task pending again, so a completion followed by a regression is rescanned with the full causal history. A failed task, successful task, repeated workflow, or cron definition is not evidence by itself; the semantic scanner must identify durable operational friction or an improvement signal.

Read the full file on GitHub · 205 lines

Files

What ships with it

1 file 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. 3d ago First seen · 205 lines · 0 tokens per session scan A 04d576331fee

Subscribe to this mod's changes

evolve is a skill published in the GitHub repository our-ark/enoch (11 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,832 tokens. 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens