/accint-frames
Drain acc's deliberation queue — open/waiting brain_frames checkpointed by headless runs — via acc_act(runtime="continue").
One skill from agentic-awesome-skills.
shell
$ npx -y skills add sickn33/agentic-awesome-skills --skill accint-frames --agent claude-codeInstalls just this skill. Get the whole plugin for auto-invocation.
How it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/accint-frames
Context preview
The summary Claude sees to decide when to auto-load this skill.
Drain acc's deliberation queue — open/waiting brain_frames checkpointed by headless runs — via acc_act(runtime="continue").
Stats
Stars43,761
Forks6,465
LanguagePython
LicenseMIT
Ships with agentic-awesome-skills
SKILL.md
accint-frames.SKILL.md
--- name: accint-frames description: Drain acc's deliberation queue — open/waiting brain_frames checkpointed by headless runs — via acc_act(runtime="continue"). risk: unknown source: https://github.com/maxbaluev/accreted-intelligence/tree/main/plugins/claude/skills/frames source_repo: maxbaluev/accreted-intelligence source_type: community date_added: 2026-07-01 license: Apache-2.0 license_source: https://github.com/maxbaluev/accreted-intelligence/blob/main/LICENSE --- # frames ## When to Use Use this skill when you need drain acc's deliberation queue — open/waiting brain_frames checkpointed by headless runs — via acc_act(runtime="continue"). Routing sugar over the two MCP verbs — no logic lives here. 1. List the queue: `acc frames` (CLI, read-only observation). 2. For each open/waiting frame: read its typed hole + retrieved context, deliberate, then submit via `acc_act(runtime="continue", input={"frame_id": ..., "submit_token": ..., "proposal_text": ...})`. 3. End `proposal_text` with `PREDICT: <0.00-1.00> <why>`; acc strips that line before the owner sees it and uses it to calibrate the Work Model against later outcomes.
