skill-orchestrator-patterns

A reusable workflow for moving an agent task through stages such as analysis, design, planning, coding, review, and revision.

In plain words
What is it for?
Use it to dispatch the right agent and reviewer, limit revision cycles, and decide when work should move to the next stage.
Why use it?
It gives each stage a defined handoff and review cycle, making multi-step work easier to coordinate.

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/matrixfounder/agentic-development/skill-orchestrator-patterns
Any agent
npx skills add MatrixFounder/Agentic-development --skill skill-orchestrator-patterns
Clone the repo
git clone --depth 1 https://github.com/MatrixFounder/Agentic-development

Made for: Claude Code, Codex.

Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,111 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 $0.00028 $0.01111
Opus 5 $0.00014 $0.00556
Sonnet 5 $0.00006 $0.00222
Haiku 4.5 $0.00003 $0.00111

Measured 2d ago against content hash 0824a93ed2c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-orchestrator-patterns 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.

.agent/skills/skill-orchestrator-patterns/SKILL.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orchestrator Patterns

This skill defines reusable patterns for the Orchestrator's pipeline stages, enabling compressed prompts.

[!IMPORTANT] Reference this skill for Stage Cycle logic. The Orchestrator uses these patterns instead of verbose per-scenario instructions.

Stage Dispatch Table

Stage Agent Prompt Reviewer Prompt Max Cycles Skill Next Stage
Analysis 02_analyst 03_task_reviewer 2 skill-archive-task Architecture
Architecture 04_architect 05_architecture_reviewer 2 architecture-design Planning
Planning 06_planner 07_plan_reviewer 2 (1 rev) planning-decision-tree Execution
Execution 08_developer 09_code_reviewer 2 (1 fix) developer-guidelines Next Task / Completion

Pattern: Stage Cycle

Applicability

  • Stages with Init → Review → Revision flow
  • Applies to: Analysis, Architecture, Planning, Execution

Init Phase

INPUT: {stage_name}, {agent_prompt}, {artifact_path}

FLOW:
1. Read agent prompt
2. Pass required context to agent
3. Wait for result: { artifact_file, blocking_questions }

DECISION:
- IF blocking_questions → STOP, ask user (Scenario 14)
- ELSE → proceed to Review

Review Phase

INPUT: {artifact_file}, {reviewer_prompt}, {iteration}

FLOW:
1. Read reviewer prompt
2. Pass artifact + context to reviewer
3. Wait for result: { review_file, has_critical_issues }

DECISION TABLE:
| Condition | Action |
|-----------|--------|
| No issues | → Next Stage |
| Issues AND iteration < max | → Revision |
| Critical issues AND iteration = max | → STOP, ask user |
| Non-critical issues AND iteration = max | → Next Stage (with warning) |

Revision Phase

INPUT: {review_file}, {original_artifact}, {agent_prompt}

INSTRUCTION TO AGENT:
"Fix comments from {review_file}. Do NOT change unrelated parts. Preserve structure."

FLOW:
1. Pass review + original to agent
2. Wait for updated artifact
3. Return to Review Phase (+1 iteration)

Read the full file on GitHub · 173 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 · 173 lines · 28 tokens per session scan A 0824a93ed2c4

Subscribe to this mod's changes

skill-orchestrator-patterns is a skill published in the GitHub repository MatrixFounder/Agentic-development (5 stars, last pushed 19d ago), licensed Apache-2.0. It adds 28 tokens to every session and 1,111 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

argent-tv-interact

Control and inspect TV apps via argent — Apple TV (tvOS), Android TV (leanback), and Amazon Fire TV (Vega). Boot the target, read focus, navigate with the D-pad remote, type, screenshot, and on Vega debug the JS runtime (evaluate, console logs, network inspector). Use when a task targets a TV (runtimeKind "tv", or…

software-mansion/argent · 107 tokens

review-offered-task

Review a task that has been offered to you and decide whether to accept or reject it.

desplega-ai/agent-swarm · 22 tokens

company-hiring-intelligence

Reverse-engineer what a company is building by scraping their job postings, careers page, LinkedIn Jobs, and engineering blog using TinyFish web agents. Use whenever a user wants to understand a company's strategic direction from hiring signals, do competitive intelligence, figure out a tech stack from job…

tinyfish-io/tinyfish-cookbook · 169 tokens

文档协作

引导用户通过结构化的文档共同编写工作流程。当用户想撰写文档、提案、技术规范、决策文档或类似结构化内容时使用。该工作流程帮助用户高效传递上下文,通过迭代优化内容,并验证文档对读者有效。当用户提到写文档、创建提案、起草规范或类似文档任务时触发。.

Tencent/WeKnora · 95 tokens

aidd-dev:08:for-sure

Iterative agent loop that tracks attempts and retries until a success condition is met. Use when the user says "for sure", "make sure", "keep trying until", "loop until done", "don't stop until", or needs guaranteed completion of a task with explicit success criteria.

ai-driven-dev/framework · 66 tokens

Swift Performance Optimization Skill

Use when investigating measured Swift or Apple-platform regressions in CPU, memory, launch, scrolling, animation hitches, image processing, energy, networking, or concurrency, or when designing performance tests and Instruments experiments. Do not use for speculative micro-optimization, ordinary refactoring, or a…

termio-sh/termio · 68 tokens