dcc-orchestration

A set of instructions for coordinating multiple coding agents on a complex task. Subagents are separate agents that can explore, review, test, or implement assigned parts of the work.

In plain words
What is it for?
Use it for parallel codebase exploration, documentation research, reviews, testing, log analysis, or clearly separated implementation tasks.
Why use it?
It helps divide independent work while keeping one agent responsible for decisions and combining the results.

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/wharley/devcommandcenter/dcc-orchestration
Any agent
npx skills add wharley/DevCommandCenter --skill dcc-orchestration
Clone the repo
git clone --depth 1 https://github.com/wharley/DevCommandCenter

Made for: Claude Code, Codex.

Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 538 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 $0.00050 $0.00538
Opus 5 $0.00025 $0.00269
Sonnet 5 $0.00010 $0.00108
Haiku 4.5 $0.00005 $0.00054

Measured 2d ago against content hash dd6bfe7ddbb3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dcc-orchestration 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.

apps/desktop/src/features/skills/presets/dcc-orchestration/SKILL.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orchestrate with Codex subagents

Coordinate specialized subagents while keeping the primary agent responsible for requirements, decisions, integration, and the final answer.

Decide whether to delegate

  • Delegate only when it materially improves speed, quality, or context isolation.
  • Prefer delegation for independent, read-heavy work such as codebase exploration, documentation research, review, test execution, log analysis, and triage.
  • Keep simple, sequential, or tightly coupled work in the primary thread.
  • Avoid parallel edits to the same files or subsystem. Partition write tasks by clear ownership boundaries.

Plan the agent team

  • Keep the primary agent as orchestrator and integrator.
  • Use the built-in explorer role for read-only codebase mapping and evidence gathering.
  • Use the built-in worker role for a bounded implementation or fix with explicit file ownership.
  • Use gpt-5.6-terra for fast exploration, review, tests, and other well-scoped supporting work. Reserve gpt-5.6-sol for a subtask that truly requires deeper ambiguous reasoning.
  • Respect the configured concurrency limit. Start the smallest useful team, normally one to three subagents.

Write bounded assignments

For every delegated task, state:

  1. The concrete objective and boundaries.
  2. Whether the task is read-only or may edit files.
  3. The files or subsystem the agent owns when edits are allowed.
  4. The evidence, validation, or output the agent must return.
  5. Relevant constraints from the user and repository instructions.

Do not delegate vague prompts such as "investigate everything". Do not ask a subagent to redo work already assigned elsewhere.

Coordinate execution

  • Spawn independent tasks in parallel when safe.
  • Continue useful primary-thread work while subagents run.
  • Send follow-up instructions only when new information materially changes an assignment.
  • Wait for every required result before concluding.
  • If delegation is unavailable or a subagent fails, continue locally when possible instead of retrying indefinitely.

Read the full file on GitHub · 52 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 52 lines · 50 tokens per session scan A dd6bfe7ddbb3

Subscribe to this mod's changes

dcc-orchestration is a skill published in the GitHub repository wharley/DevCommandCenter (9 stars, last pushed 2d ago), licensed Apache-2.0. It adds 50 tokens to every session and 538 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.