What is orchestrator?

An orchestration agent that coordinates the stages of the Skill Forge Loop, a process for testing and improving agent skills.

It assembles experiment context, tracks exploration and reuse phases, passes data between agents, and gathers near-miss results for future decisions.

It keeps information consistent between the hypothesis, editing, and scoring stages and decides what happens next.

orchestrator — Agent for coding agents by GodModeAI2025: An orchestration agent that coordinates the stages of the…

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add agents/godmodeai2025/skill-forge/orchestrator

Clone the repo

git clone --depth 1 https://github.com/GodModeAI2025/skill-forge

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/agents/godmodeai2025/skill-forge/orchestrator.svg)](https://agentmods.dev/agents/godmodeai2025/skill-forge/orchestrator)

Your own site

<a href="https://agentmods.dev/agents/godmodeai2025/skill-forge/orchestrator"><img src="https://agentmods.dev/badge/agents/godmodeai2025/skill-forge/orchestrator.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,488 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.02488
Opus 5	$0.00000	$0.01244
Sonnet 5	$0.00000	$0.00498
Haiku 4.5	$0.00000	$0.00249

Measured 4d ago against content hash 189d5f12e419, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

orchestrator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

agents/orchestrator.md · 227 lines

How it starts

The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orchestrator Agent

Koordiniert den Agent-Lifecycle im Skill Forge Loop.

Rolle

Du bist der "Dirigent" im Skill Forge Loop. Du verwaltest den Informationsfluss zwischen Hypothesis, Mutator und Scorer Agent, triffst Meta-Entscheidungen und sorgst für Konsistenz über den gesamten Experiment-Zyklus.

Verantwortlichkeiten

1. Context Assembly

Vor jedem Agent-Aufruf:

Lade templates/agent_context.md
Fülle es mit aktuellen Daten aus:
- history.json (via composite_score.py agent-history)
- coverage-matrix.json
- checkpoint.json (falls vorhanden)
Bestimme die aktuelle Phase:
- Runde 1-3: Exploration (80% unberührte Kategorien bevorzugen)
- Runde 4-7: Balanced (50/50 Exploration/Exploitation)
- Runde 8+: Exploitation (80% erfolgreiche Kategorien vertiefen)
Sammle Near-Miss-Hypothesen aus decision.json Dateien
Hänge den gefüllten Context an den Agent-Prompt an

2. Agent-Übergabe-Protokoll

Der Datenfluss zwischen Agenten folgt einem strikten Protokoll:

Orchestrator
    │
    ├─▶ Hypothesis Agent
    │     Input:  history_grouped + history_recent + coverage + near_misses + context
    │     Output: hypothesis.json (validiert gegen Output Schema)
    │
    ├─▶ Mutator Agent
    │     Input:  hypothesis.json + target_path + snapshot_dir + context
    │     Output: mutation.json (validiert gegen Output Schema)
    │
    ├─▶ [Experiment-Run] (Eval/Command)
    │
    ├─▶ Scorer Agent (nur Skill-Modus)
    │     Input:  eval_prompt + output_dir
    │     Output: grading.json pro Lauf und Seite, plus comparison.json
    │             pro Experiment (nur mit use_comparator). Eine Datei
    │             namens scoring.json gibt es nicht.
    │
    └─▶ Decision + Checkpoint
          Input:  candidate_score + baseline_score + config.json
          Aufruf: composite_score.py decide --candidate <s> --baseline <s> \
                    --config <workspace>/config.json
          Output: decision.json + checkpoint.json

Read the full file on GitHub · 227 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

4d ago First seen · 227 lines · 0 tokens per session scan A 189d5f12e419

Subscribe to this mod's changes

orchestrator is an agent published in the GitHub repository GodModeAI2025/skill-forge (17 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,488 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Autonomous Agents Building agents agents ai automation autoresearch claude

benchmark-reviewer

Reviews an evo benchmark in two modes. mode=audit -- pre-flight harness audit before the first run (per-task instrumentation, leakage, gates, plumbing); read-only. mode=review-experiment -- post-commit per-task failure analysis for a specific experiment; reads per-task traces and the eval-runner log, writes per-task…

evo-hq/evo · 112 tokens

ideator

Generates ranked experiment proposals for the evo orchestrator. Runs ONE brief per invocation (failureanalysis, literature, or frontierextrapolation) and appends proposals as JSONL lines to a shared file the orchestrator reconciles. Use literature for web/arXiv/HF/GitHub research (the only brief that needs network).…

evo-hq/evo · 142 tokens

verifier

Read-only audit of one evo experiment for design-time cheating (pre-phase) or result-time validity (post-phase). Catches test-set leakage in training data, subsetted eval commands, missing gates for new artifacts, generic hypotheses, cache short-circuits, fake artifacts, and score-reproducibility failures. Returns…

evo-hq/evo · 146 tokens

autoresearch-orchestrator

Use this agent to run an autoresearch experiment session end-to-end — setup, baseline, and a batch of edit→measure→keep/discard experiments — and return a structured checkpoint. Typical triggers include the /run-autoresearch command dispatching a new optimization goal, resuming an existing session found in…

proyecto26/autoresearch-ai-plugin · 115 tokens

eval-doctor

This agent is spawned in two situations.

zircote-plugins/autoresearch · 0 tokens

convergence-reporter

Agent "convergence-reporter" from zircote-plugins/autoresearch, covering convergence reporter agent, context, role, inputs and process.