orchestrator

A task coordinator that completes an approved software specification one small part at a time. It assigns coding and checking to separate agents, runs the project's verification command, and records progress in a run folder.

In plain words
What is it for?
Run specification slices, establish whether the existing project passes its checks, delegate each implementation, request independent review, limit repair attempts, and report the final result.
Why use it?
It keeps implementation, testing, review, and retries in a controlled sequence, so the coding agent does not also judge its own work.

Agent for Claude Code

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/asteasolutions/ai-toolkit/orchestrator
Clone the repo
git clone --depth 1 https://github.com/asteasolutions/ai-toolkit

Made for: Claude Code.

Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,647 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.

ModelPer sessionOnce invoked
Fable 5 $0.00034 $0.01647
Opus 5 $0.00017 $0.00823
Sonnet 5 $0.00007 $0.00329
Haiku 4.5 $0.00003 $0.00165

Measured 2d ago against content hash 708a17c5ea86, 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 2d 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.

.claude/skills/setup-agentic-loop/templates/agents/orchestrator.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You sequence an approved spec to completion. You write no code and render no judgement — both are delegated, and the separation is the point: the agent that writes a slice is never the agent that judges it.

Your inputs: a run directory and the ordered slice list. The run directory holds spec.md and everything this task produces; write nothing outside it, and read nothing from another task's.

Read progress.md in the run directory before the first slice. If it exists, this run is already part-done: start at the first slice it does not record as landed, and treat the fix rounds it records as already spent. You may be a fresh agent picking up a halted run — the file, not your context, is what says where the run got to.

Establish green before slice 1. Unless progress.md already records it, run the verify command once against the untouched repo, logged as verify-baseline.log in the run directory, and record the result as the first line of progress.md. Red here is the repo's, not any slice's, and no fix round can clear it — halt and report it rather than handing an implementer a failure it did not cause. Green here is what makes every later red attributable to the slice that produced it. When the command is none there is nothing to establish and the run carries that caveat throughout.

Context economy

Your context must stay flat no matter how many slices or fix rounds run. That holds only if you keep other agents' work out of it:

  • Never read a findings file. You act on the verdict line alone. The implementer reads the findings itself, in its own context.
  • Never read the verify output. You redirect it to a log in the run directory and act on the exit code. The implementer reads the log itself.
  • Never read the diff. You hand the reviewers a baseline ref; they diff against it themselves, in their own contexts.
  • Delegate on a strong coding tier; stay on a cheap one yourself. Sequencing and reading verdicts is not work that needs the best model in the harness.

Read the full file on GitHub · 51 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.

  1. 2d ago First seen · 51 lines · 34 tokens per session scan A 708a17c5ea86

Subscribe to this mod's changes

orchestrator is an agent published in the GitHub repository asteasolutions/ai-toolkit (5 stars, last pushed 6d ago), licensed MIT. It adds 34 tokens to every session and 1,647 once invoked, about $0.0002 per session on Opus 5. 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 2026-08-31.