Agent Evolution instructions

26 tagged Agent Evolution, measured the same way as everything else here.

capability-evolver

01

EvoMap/evolver

Skill Claude CodeCodex

A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution. Communicates with EvoMap Hub via local Proxy mailbox.

9.0k +10 2d ago A 40 tokens GPL-3.0

EvoMap/awesome-agent-evolution

Instructions file CodexOpenCode

AGENTS.md instructions for EvoMap/awesome-agent-evolution, covering cursor cloud specific instructions, required runtime, key scripts (see contributing.md for the full table), linting / testing and contribution workflow.

202 3d ago A 407 tokens

harness-evolver

05

raphaelchristi/harness-evolver

Plugin Claude Code

LangSmith-native autonomous agent optimization — evolves LLM agent code using multi-agent proposers, LangSmith experiments, and git worktrees.

49 +1 4mo ago A tokens not measured original MIT

dev:release

06

raphaelchristi/harness-evolver

Skill Claude CodeCodex

Use when the user wants to release a new version, publish to npm, create a GitHub release, bump version, or tag a release. Also use when the user says 'release', 'publish', 'bump version', 'tag', or 'npm publish'.

49 +1 4mo ago A 58 tokens original MIT

raphaelchristi/harness-evolver

Instructions file

Instructions for raphaelchristi/harness-evolver, covering claude.md, what this is, dependencies, running tools locally and use --no-canary to skip preflight check.

49 +1 4mo ago A 3,303 tokens original MIT

harness-architect

08

raphaelchristi/harness-evolver

Agent

Use this agent when the evolution loop stagnates or regresses. Analyzes the agent architecture and recommends topology changes (single-call → RAG, chain → ReAct, etc.).

49 +1 4mo ago A 43 tokens original MIT

harness-evaluator

09

raphaelchristi/harness-evolver

Agent

Use this agent to evaluate experiment outputs using LLM-as-judge. Reads run inputs/outputs from LangSmith via langsmith-cli, judges correctness, and writes scores back as feedback. No external API keys needed.

49 +1 4mo ago A 48 tokens original MIT

harness-proposer

10

raphaelchristi/harness-evolver

Agent

Self-organizing agent optimizer. Investigates a data-driven lens (question), decides its own approach, and modifies real code in an isolated git worktree. May self-abstain if it cannot add meaningful value.

49 +1 4mo ago A 49 tokens original MIT

SessionStart

11

raphaelchristi/harness-evolver

Hook

Runs when a session starts, executing session-start.sh via bash. From raphaelchristi/harness-evolver.

49 +1 4mo ago A tokens not measured copy · 55% MIT

harness:evolve

12

raphaelchristi/harness-evolver

Skill Claude CodeCodex

Use when the user wants to run the optimization loop, improve agent performance, evolve the agent, or iterate on quality. Requires .evolver.json to exist (run harness:setup first).

49 +1 4mo ago A 43 tokens original MIT

harness:setup

13

raphaelchristi/harness-evolver

Skill Claude CodeCodex

Use when the user wants to set up the evolver in their project, optimize an LLM agent, improve agent performance, or mentions evolver for the first time in a project without .evolver.json.

49 +1 4mo ago A 47 tokens original MIT

At most 3 mods per repository are shown here — the rest are on their repository pages: