Skip to content

VoidLight00/deo-harness

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

DEO — a mythic conductor orchestrating agent orbs of different effort levels

DEO — Dynamic Effort Orchestration

A Claude Code + Fable 5 harness that decomposes a goal into tasks and dynamically assigns each sub-agent the effort level its complexity deserves.

English | 한국어

License Version Model Fallback


DEO spends compute where it matters. Routine tasks run at low effort, ordinary work at medium, architecture and planning at high, and the single final verification gate at xhigh — never the other way around. Every agent stays on Fable 5; cost control comes from effort differentiation, not model downgrading.

Why effort, not models

Effort is the primary lever for intelligence, latency, and cost on Fable 5. Splitting work across cheaper models routes tasks away from the model this harness exists to use — and Fable 5 at lower effort frequently beats older models at their highest settings. So DEO keeps one model and varies one knob.

Task class Examples Effort
Simple / Routine code conversion, data cleanup, simple analysis low
Medium general reasoning, mid-size code changes medium
High architecture design, complex planning, hard debugging high
Ultra-critical final verification, security review, creative problem-solving xhigh

The single source of truth for this matrix — including the dispatch-phrase mapping that implements it — lives in skills/deo-pipeline/SKILL.md. No other file duplicates it.

How it works

flowchart LR
    A[Goal] --> B["deo-planner<br/>(high)<br/>PLAN.json"]
    B --> C["deo-executor ×N<br/>(per-task effort)<br/>parallel dispatch"]
    C --> D["deo-verifier<br/>(high, fresh context)<br/>per-task gate"]
    D -->|PASS| C
    D -->|3 tasks done| E["send_to_user<br/>progress report"]
    C --> F["deo-verifier<br/>(xhigh, once)<br/>final gate"]
    F --> G["✅ DEO workflow complete"]
Loading
  1. Plandeo-planner turns your goal into PLAN.json: task breakdown, dependencies, per-task effort, optional swarm grouping.
  2. Execute — independent tasks dispatch to deo-executor agents in parallel, each with an effort-steering phrase injected into its prompt.
  3. Verify — every finished task is judged by deo-verifier in a fresh context (no shared blind spots), then the workflow advances automatically.
  4. Report — every 3 tasks, a send_to_user progress report: completed tasks with evidence, artifact sizes, effort distribution. Post-hoc facts, never countdown pressure.
  5. Finish — one xhigh final gate over everything, then the ✅ DEO workflow complete marker, a plain-language summary, and optional human-review pointers.

Honest effort mechanics

Claude Code's agent dispatch has no effort parameter. DEO does not pretend it does. Effort is implemented two real ways:

  1. Dispatch-phrase injection — each level maps to a phrase that steers deliberation depth (e.g. low → "routine task, no over-deliberation, skip self-review").
  2. Verification-depth differentiationlow skips self-checks entirely; xhigh requires fresh-context cross-verification with evidence attached to every claim.

Runtime control

While a workflow runs:

effort 변경: T3 xhigh        # one task
effort 변경: collect-swarm low   # a whole swarm
effort 변경: 전체 medium       # the default for everything not yet started

Changes apply from the next dispatch; in-flight tasks finish at their current level. Priority: task > swarm > default (high).

Repository layout

Path Role
skills/deo-pipeline/SKILL.md Orchestrator skill — 6-step workflow, Effort Matrix (SSoT), runtime change rules
skills/deo-pipeline/references/ Memory-system design, send_to_user tool schema, autonomy reminders, fresh-context verifier pattern
agents/deo-planner.md Goal → PLAN.json (task breakdown + effort assignment)
agents/deo-executor.md Generic executor — works at the effort level its dispatch prescribes
agents/deo-verifier.md Fresh-context verifier — judges artifacts only, PASS/FAIL with evidence
state/STATE-template.md Handoff/resume state snapshot template
docs/CLAUDE-block.md Routing block to paste into your ~/.claude/CLAUDE.md

Installation

git clone https://github.com/VoidLight00/deo-harness.git
cd deo-harness

# 1. Skill (including references/)
cp -R skills/deo-pipeline ~/.claude/skills/deo-pipeline

# 2. State template (under the skill directory)
cp -R state ~/.claude/skills/deo-pipeline/state

# 3. Agents
cp agents/deo-planner.md agents/deo-executor.md agents/deo-verifier.md ~/.claude/agents/

Then paste the two blocks from docs/CLAUDE-block.md into your ~/.claude/CLAUDE.md routing table and safety-rules section.

Verify the install: open a new Claude Code session and type /deo status — the deo-pipeline skill should respond.

Usage

/deo Organize the 30 meeting notes in this folder into a weekly report

That's it. Task decomposition and effort assignment are automatic. If a session drops, /deo resume <run_id> picks up from the STATE.md snapshot — no prior conversation needed.

Safe to customize: the example column of the Effort Matrix. Do not change: the level names (low/medium/high/xhigh), the "xhigh only at the final gate, once" rule, the model: fable line in agent definitions, and the no-duplication SSoT rule — these are what keep cost control and consistency intact.

Differences from the original DEO design

This harness was generated and gated by Fable Forge from a third-party design document. Four corrections were applied:

Original design This harness Why
Spawn "Opus 4.8 sub-agents" for cheap work All agents pin model: fable; cost control via effort Old-model pins route work away from Fable 5 (Fallback-Zero HARD rule FZ2). Effort differentiation achieves the original intent — cost/performance balance — within one model
Configure via a "Custom Instructions sidebar" skill + agents + CLAUDE.md routing block No such UI exists in Claude Code; this is the real extension mechanism
Per-agent effort as an API parameter Dispatch-phrase injection + verification-depth differentiation The agent dispatch has no effort parameter; DEO implements the effect honestly instead of prescribing a parameter that does not exist
Real-time token-remaining display Post-hoc reports every 3 tasks (tasks, evidence, artifact sizes, effort distribution) Exposing countdown numbers to the model induces premature session wrap-up (FZ6). Users need progress evidence, not pressure metrics

Verification

All artifacts pass the Fable Forge fallback-zero HARD gate:

bash ~/fable-forge/gates/fable_lint.sh .
echo "exit: $?"   # must be 0

If you edit the skill or agent definitions, re-run the gate on your copy — pass/fail is decided by the script's exit code only, never by self-report.

License

MIT © 2026 VOIDLIGHT

About

Dynamic Effort Orchestration — a Claude Code + Fable 5 harness that assigns each sub-agent the effort level its task deserves. Zero Opus fallback.

Topics

Resources

License

Contributing

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors