atlas-orchestrate

A local workflow coordinator for coding agents that lets you define connected steps, checks, reviews, and approvals.

In plain words
What is it for?
Use it for workflows with several agents, independent reviews, repeated checks, human approval, or changes across separate Git worktrees. It can run work immediately or in the background and resume interrupted runs.
Why use it?
It helps manage multi-step agent work without losing track of order, limits, safety boundaries, or cost. It also supports checking and previewing a workflow before it makes billable model calls.

Skill for Claude CodeCodex

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 skills/ctrl1candv/atlas/skill
Any agent
npx skills add Ctrl1CandV/Atlas --skill skill
Clone the repo
git clone --depth 1 https://github.com/Ctrl1CandV/Atlas

Made for: Claude Code, Codex.

Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,311 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 $0.00057 $0.04311
Opus 5 $0.00028 $0.02155
Sonnet 5 $0.00011 $0.00862
Haiku 4.5 $0.00006 $0.00431

Measured yesterday against content hash 3583e634fb18, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

atlas-orchestrate 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 yesterday.

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.

skill/SKILL.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Atlas workflow orchestration

Atlas 0.1.0 is a local, source-only Windows release. ${ATLAS_HOME} means the user's absolute source root; this document contains no machine-specific path. The observer runs at http://127.0.0.1:8321 after the user starts it.

Use a single model call for simple one-step work. Use Atlas for explicit graph structure, bounded review loops, independent model perspectives, coding-agent worktree changes, or human approval.

Required sequence

  1. Design YAML with explicit inputs, outputs, routes, and guards.
  2. Call atlas_validate_workflow (zero provider calls).
  3. Call atlas_save_workflow only when persistence is requested.
  4. Call atlas_run_workflow with dry_run: true (zero provider calls and no run directory).
  5. Show unresolved model choices, graph shape, guard limits, agent security boundaries, privacy, and cost implications.
  6. Call atlas_run_workflow with dry_run: false only after explicit execution intent. Default is synchronous (wait=true); for long graphs pass wait=false to get a run_id immediately after preflight instead of blocking the session (mutually exclusive with persist_as).
  7. Call atlas_get_run to inspect a created run, atlas_list_runs to page through runs. If and only if its dynamic status is interrupted, use atlas_resume_run; paused human decisions remain in the local Web UI (which also offers the cancel button for running/waiting runs). To stop a run, atlas_cancel_run requests cooperative cancellation — the request cannot be revoked; paused/interrupted runs become cancelled directly, and a local_cli agent execution in flight is terminated with its whole process tree, while SDK-backed model calls finish their current attempt before the next consumption point ends the run.

While a dispatch is in flight, the controller appends node_progress heartbeat events to the run ledger (node/iteration/attempt/model/elapsed_ms/phase; default 30s, run-level via ATLAS_NODE_HEARTBEAT_INTERVAL_S). They prove only that the controller is still waiting — never model-internal progress — and stop before any terminal event, so a long silence after the last heartbeat means the call is still running, not that the stream died.

Read the full file on GitHub · 127 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. yesterday First seen · 127 lines · 57 tokens per session scan A 3583e634fb18

Subscribe to this mod's changes

atlas-orchestrate is a skill published in the GitHub repository Ctrl1CandV/Atlas (3 stars, last pushed 3d ago), licensed Apache-2.0. It adds 57 tokens to every session and 4,311 once invoked, about $0.0003 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.