url/SkillOpt
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(plugins): ship SkillOpt-Sleep for Claude Code, Codex, and Copilot

Browse Source 
Restructure into plugins/{claude-code,codex,copilot}/ — one engine, three thin
shells, all calling the shared plugins/run-sleep.sh -> python -m skillopt_sleep.

  - claude-code/: existing plugin moved here; runner delegates to the shared
    launcher (fixes repo-root resolution after the move).
  - codex/: ~/.codex/prompts/sleep.md custom prompt + ~/.agents/skills SKILL.md +
    install.sh + AGENTS.md hint — Codex's documented, stable extension surfaces.
  - copilot/: a stdlib-only MCP server (mcp_server.py) exposing sleep_* tools,
    plus mcp-config.example.json and a copilot-instructions snippet. Verified end
    to end (initialize -> tools/list -> tools/call returns real engine output).
  - plugins/README.md overview table; main README News + a dedicated SkillOpt-Sleep
    section; pyproject lists skillopt_sleep as a first-class package.

Decoupling emphasized throughout: open-source tool (skillopt_sleep/) with zero
dependency on the research package. 29 tests pass; all three shells resolve.

Co-Authored-By: Claude Opus 4 <noreply@anthropic.com>
This commit is contained in:
Yifan Yang
2026-06-08 14:31:52 +00:00
parent b02ffc2c99
commit f9db99853b
22 changed files with 576 additions and 31 deletions
Download Patch File Download Diff File Expand all files Collapse all files
plugins/codex/skills/skillopt-sleep/SKILL.md
+49
View File
@@ -0,0 +1,49 @@
---
name: skillopt-sleep
description: Nightly offline self-evolution for a Codex agent. Reviews past sessions, replays recurring tasks, and consolidates validated memory + skills behind a held-out gate. Use when the user wants Codex to learn from past usage, run a "sleep"/"dream" cycle, or schedule offline self-optimization.
---
# SkillOpt-Sleep (Codex skill)
This skill drives the `skillopt_sleep` engine — an offline "sleep cycle" that
makes a Codex agent better at the user's recurring work without retraining.
## When to use
Trigger when the user wants to: review past sessions, learn their preferences,
consolidate feedback into long-term memory/skills, run a nightly/offline
self-improvement cycle, or adopt a staged proposal.
## How to run it
Invoke the bundled runner via shell (Codex `exec` has shell access). The runner
finds the engine and a Python ≥ 3.10 automatically:
```bash
# point at the repo if it isn't auto-detected from CWD:
export SKILLOPT_SLEEP_REPO=/path/to/SkillOpt-Sleep
bash "$SKILLOPT_SLEEP_REPO/plugins/run-sleep.sh" <action> --project "$(pwd)"
```
`<action>` ∈ `status | dry-run | run | adopt | harvest`. Use `--backend codex`
for real improvement on the user's own Codex budget (default `mock` = no spend).
## Steps
1. Run the requested action; capture stdout.
2. For `run`/`dry-run`: read the staged `report.md` it prints and show the user
the held-out baseline → candidate score and the exact proposed edits.
3. `run` only **stages** a proposal under `<project>/.skillopt-sleep/staging/`;
nothing live changes until `adopt`. Offer `/sleep adopt`.
4. Never hand-edit the user's `AGENTS.md` / skills yourself — only `adopt` does,
and it backs up first.
## Validate
```bash
python -m skillopt_sleep.experiments.run_gbrain --backend codex \
--seeds brief-writer --data-root /path/to/gbrain-evals/eval/data/skillopt-v1 \
--nights 2 --limit-replay 3 --limit-holdout 3
```
A deficient skill goes 0.00 → 1.00 on a held-out set; the optimizer's edits are
gated on real-task performance.