How do I install the Tao Loop skill?

Run npx skillmds@latest add cleanexpo/tao-loop in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Tao Loop safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Tao Loop?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Tao Loop free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Tao Loop?

cleanexpo (@cleanexpo) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Tao Loop by cleanexpo — Agent Skill

Name: Tao Loop
Author: cleanexpo

Tao Loop

Judge-gated autonomous coding loop runner. Port of pi-until-done's `/goal ... Ralph` pattern with single-metric termination via `tao_judge.judge`. One worker step per iteration, optional judge call every N iters, three independent abort axes from `kill_switch.LoopCounter` (MAX_ITERS, MAX_COST, HARD_STOP).

cleanexpo d44dcad 2.4 KB Updated Sep 17, 2026

File contents

tao-loop

Iterates a generator step + judge step until the judge says done or the kill-switch fires. Returns a fully-populated LoopResult; never raises KillSwitchAbort to the caller.

When to trigger

A user issues an autonomy-class brief that warrants more than one iteration.
A higher-level orchestrator wants a budget-bounded, judge-gated worker loop rather than the wave-orchestrated path.

Public API

from app.server.tao_loop import run_until_done, LoopResult

result = await run_until_done(
    goal="implement X",
    workspace="/path/to/repo",
    max_iters=10,                # else honour TAO_MAX_ITERS
    max_cost_usd=1.50,           # else honour TAO_MAX_COST_USD
    judge_every_n_iters=2,       # cost-control knob
    timeout_per_iter_s=600,
    evt: ...,    # streamed iter_complete payloads
)
# result.done; result.reason; result.iters; result.cost_usd;
# result.judge_history; result.final_state

Autoresearch envelope

The judge's score ∈ [0, 1] is the single termination scalar. The kill-switch provides the orthogonal cost / iteration / hard-stop bounds.

Kill-switch dependency

RA-1966's LoopCounter is constructed once per loop. tick() advances iters and adds cost atomically, raising KillSwitchAbort on any breach — captured into LoopResult.reason.

CLI

python scripts/run_tao_loop.py --goal "..." --workspace /path --max-iters N --max-cost X --judge-every N

Lookahead mode (OM-1 / RA-1970)

Set TAO_OM1_ENABLED=1 for a 15-step default horizon, or TAO_PLANNER_HORIZON=1..20 explicitly. The loop decomposes the goal up front via the Opus orchestrator planner, executes one step per iteration, and re-plans on stall or horizon exhaustion (capped by TAO_PLANNER_MAX_REPLANS, default 2).

result = await run_until_done(
    goal="implement X",
    workspace="/path/to/repo",
    planner_horizon=15,   # or omit and rely on OM-1 / env
    max_replans=2,
    ...
)

Status: GET /api/autonomy/status → planner block (mode, effective_horizon).

---name: tao-loopdescription: Judge-gated autonomous coding loop runner. Port of pi-until-done's `/goal ... Ralph` pattern with single-metric termination via `tao_judge.judge`. One worker step per iteration, optional judge call every N iters, three independent abort axes from `kill_switch.LoopCounter` (MAX_ITERS, MAX_COST, HARD_STOP).---# tao-loopIterates a generator step + judge step until the judge says done or the kill-switchfires. Returns a fully-populated LoopResult; never raises KillSwitchAbort to thecaller.## When to trigger- A user issues an autonomy-class brief that warrants more than one iteration.- A higher-level orchestrator wants a budget-bounded, judge-gated worker loop rather than the wave-orchestrated path.## Public API```pythonfrom app.server.tao_loop import run_until_done, LoopResultresult = await run_until_done( goal="implement X", workspace="/path/to/repo", max_iters=10, # else honour TAO_MAX_ITERS max_cost_usd=1.50, # else honour TAO_MAX_COST_USD judge_every_n_iters=2, # cost-control knob timeout_per_iter_s=600, on_event=lambda evt: ..., # streamed iter_complete payloads)# result.done; result.reason; result.iters; result.cost_usd;# result.judge_history; result.final_state```## Autoresearch envelopeThe judge's `score` ∈ [0, 1] is the single termination scalar. The kill-switchprovides the orthogonal cost / iteration / hard-stop bounds.## Kill-switch dependencyRA-1966's `LoopCounter` is constructed once per loop. `tick()` advances itersand adds cost atomically, raising `KillSwitchAbort` on any breach — capturedinto `LoopResult.reason`.## CLI`python scripts/run_tao_loop.py --goal "..." --workspace /path --max-iters N --max-cost X --judge-every N`### Lookahead mode (OM-1 / RA-1970)Set `TAO_OM1_ENABLED=1` for a 15-step default horizon, or `TAO_PLANNER_HORIZON=1..20`explicitly. The loop decomposes the goal up front via the Opus orchestrator planner,executes one step per iteration, and re-plans on stall or horizon exhaustion(capped by `TAO_PLANNER_MAX_REPLANS`, default 2).```pythonresult = await run_until_done( goal="implement X", workspace="/path/to/repo", planner_horizon=15, # or omit and rely on OM-1 / env max_replans=2, ...)```Status: `GET /api/autonomy/status` → `planner` block (`mode`, `effective_horizon`).

Frequently asked questions