New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Orchestration Patterns

by bybren-llc in bybren-llc/safe-agentic-workflow

Agentic orchestration patterns for long-running tasks. An agent skill from bybren-llc/safe-agentic-workflow.

MITAuto-check: notesAgent Workflows

Install Orchestration Patterns

skills CLI
$ npx skills add bybren-llc/safe-agentic-workflow --skill orchestration-patterns -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install bybren-llc/safe-agentic-workflow orchestration-patterns --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/bybren-llc/safe-agentic-workflow.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/orchestration-patterns .claude/skills/orchestration-patterns && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
orchestration-patterns
GitHub stars
423
Token cost
~2k tokens
SKILL.md length
373 words
Files
2
Skills in repo
42
Repo updated
First seen
Licence
MIT

At a glance

Agentic orchestration patterns for long-running tasks. An agent skill from bybren-llc/safe-agentic-workflow.

  • Works in 4 steps: Separation of Concerns: QAS validates… → Independent Verification: Catches what… → Bias Prevention: Fresh eyes on commit… → …
  • Managing multi-step work
  • SKILL.md covers Purpose, When This Skill Applies, Simon Willison's Agent Loop and Evidence-Based Delivery, plus 6 more sections
  • Calls yarn

What it does

Orchestration Patterns is an agent skill from bybren-llc/safe-agentic-workflow. Agentic orchestration patterns for long-running tasks. Implements evidence-based delivery and Simon Willison's agent loop. Use when managing multi-step work, coordinating subagents, or orchestrating PR workflows.

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `README.md`).

It sits in Agent Workflows, covering Autonomous loops, Subagents and Multi-agent orchestration. The repository describes itself as: SAW — SAFe Agentic Workflow AI Agent Harness for Multi-Agent Team Workflows Built on SAFe methodology (Scaled Agile Framework), adapted for AI agent teams (Now With AI-DLC!)… The licence is MIT.

When your agent uses it

  • Managing multi-step work
  • Coordinating subagents
  • Orchestrating PR workflows

Example prompts

  • “/orchestration-patterns”

Requirements

  • Pre-approved tools (allowed-tools): Read, Bash, Grep, Glob, Task

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Separation of Concerns: QAS validates but doesn't write product code
  2. Independent Verification: Catches what implementer missed
  3. Bias Prevention: Fresh eyes on commit messages, patterns
  4. Evidence in Linear: QAS posts final evidence + verdict to Linear (system of record)

What it can do on your machine

Read from SKILL.md and the folder at commit 26ca58b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Bash
    • Grep
    • Glob
    • Task

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • yarn

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use yarn, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Orchestration Patterns loads about 2k tokens when it runs. Until then it costs about 59 tokens; SKILL.md has 373 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~59
When it runs · the whole SKILL.md, loaded when a task matches
~2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Bash, Grep, Glob, Task

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from bybren-llc/safe-agentic-workflow at commit 26ca58b, republished under its MIT licence (© bybren-llc). 373 words, ~1,956 tokens.

Download SKILL.mdSave it as .claude/skills/orchestration-patterns/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
orchestration-patterns
description
Agentic orchestration patterns for long-running tasks. Implements evidence-based delivery and Simon Willison's agent loop. Use when managing multi-step work, coordinating subagents, or orchestrating PR workflows.
allowed-tools
Read, Bash, Grep, Glob, Task

Orchestration Patterns Skill

Purpose

Codify evidence-based delivery and iterative agent loop for orchestrating complex, long-running tasks. These patterns ensure verifiable progress and intelligent escalation.

When This Skill Applies

Invoke this skill when:

  • Orchestrating multi-step implementation tasks
  • Managing work across multiple subagents
  • Running long-running sessions that need checkpoints
  • Preparing PRs for merge (mandatory QAS gate)
  • Coordinating team handoffs

Simon Willison's Agent Loop

Core Philosophy: "Iterate until success or blocked, then escalate."

text
┌─────────────────────────────────────────────────────────┐
│  THE AGENT LOOP (for every task)                       │
├─────────────────────────────────────────────────────────┤
│                                                         │
│  1. GOAL DEFINITION                                     │
│     └─ Clear acceptance criteria (from BSA/ticket)      │
│                                                         │
│  2. PATTERN DISCOVERY                                   │
│     └─ Search codebase, docs, previous sessions         │
│     └─ Use: pattern-discovery skill (auto-invoked)      │
│     └─ Or: /search-pattern for explicit code search     │
│                                                         │
│  3. ITERATIVE EXECUTION LOOP:                           │
│     ┌─────────────────────────────────────────────┐     │
│     │  Implement approach                         │     │
│     │       ↓                                     │     │
│     │  Run validation (yarn ci:validate)          │     │
│     │       ↓                                     │     │
│     │  If PASS → proceed to evidence              │     │
│     │  If FAIL → analyze error, adjust, repeat    │     │
│     │  If BLOCKED → escalate to TDM with context  │     │
│     └─────────────────────────────────────────────┘     │
│                                                         │
│  4. EVIDENCE ATTACHMENT                                 │
│     └─ Attach proof to Linear (see templates below)     │
│                                                         │
│  5. QAS GATE (MANDATORY before merge)                   │
│     └─ Invoke QAS subagent for independent review       │
│                                                         │
└─────────────────────────────────────────────────────────┘

Evidence-Based Delivery

Core Principle: "All work requires verifiable evidence - no 'trust me, it works'"

Evidence Types
TypeWhat It ProvesExample
Test ResultsCode works as expectedyarn ci:validate output
ScreenshotsUI changes are correctBefore/after comparison
Command OutputOperations completedBuild logs, migration logs
QAS ReportIndependent verificationQA validation markdown
Session IDFull audit trail availableClaude Code session ref
Phase Evidence Requirements
PhaseEvidence RequiredLinear Template
DevTest results, command outputDev Evidence Template
StagingUAT validation or N/A + reasonStaging Template
DoneQAS report, merge confirmationDone Evidence Template

QAS Pre-Merge Gate

MANDATORY: Before merging any PR, invoke QAS for independent review.

Why QAS Gate Matters
  1. Separation of Concerns: QAS validates but doesn't write product code
  2. Independent Verification: Catches what implementer missed
  3. Bias Prevention: Fresh eyes on commit messages, patterns
  4. Evidence in Linear: QAS posts final evidence + verdict to Linear (system of record)
QAS Invocation Pattern
text
# After implementation complete, before merge:
Task tool: QAS subagent
Prompt: "Review PR #XXX for {{TICKET_PREFIX}}-YYY. Validate:
  - Commit message format (ticket in subject line)
  - Code patterns (RLS, naming, structure)
  - CI status (all checks passing)
  - Evidence attachments in Linear
  Generate validation report to docs/agent-outputs/qa-validations/"
Show full SKILL.md (148 more words)Show less
QAS Output Location

All QAS reports go to: docs/agent-outputs/qa-validations/{{TICKET_PREFIX}}-{number}-qa-validation.md

Escalation Patterns

When to Escalate
ConditionEscalate ToInclude
Blocked > 4 hoursTDMFull context, attempts made
Architecture ambiguityARCHitectOptions, trade-offs
Cross-team dependencyTDMWhich teams, what's blocked
Security concernSecEngSpecific risk, evidence
Escalation Template
markdown
**Escalation Required**

**Blocked On**: [specific blocker]
**Attempts Made**:

1. [what you tried]
2. [what you tried]

**Context**:

- Ticket: {{TICKET_PREFIX}}-XXX
- Session ID: [if available]
- Time blocked: X hours

**Request**: [specific ask - what do you need?]

Long-Running Task Checkpoints

For tasks spanning multiple tool calls or sessions:

Checkpoint Pattern
text
Every 10-15 tool calls:
1. Update todo list with current progress
2. If nearing context limit, summarize state
3. If handoff needed, provide continuation context

At session boundaries:
1. Summarize completed work
2. List remaining items
3. Document any blockers
4. Attach evidence to Linear
State Preservation
markdown
**Session Checkpoint**

**Completed**:

- [x] Task 1
- [x] Task 2

**In Progress**:

- [ ] Task 3 (at step X)

**Remaining**:

- [ ] Task 4
- [ ] Task 5

**Blockers**: [if any]

**Next Action**: [specific next step]

Orchestration Workflow Example

text
# Complete workflow for feature implementation:

1. /start-work {{TICKET_PREFIX}}-XXX
   └─ Syncs to dev, creates branch, sets context

2. Pattern discovery (skill auto-invokes or use /search-pattern)
   └─ Finds relevant patterns before implementation

3. [Implementation with agent loop]
   ├─ Implement
   ├─ Validate (yarn ci:validate)
   ├─ Adjust if needed
   └─ Repeat until passing

4. /pre-pr
   └─ Full validation checklist

5. Create PR with evidence

6. [QAS GATE - MANDATORY]
   └─ Invoke QAS subagent for review
   └─ Fix any blocking issues
   └─ Commit QAS report

7. Merge (only after QAS approval)

8. /end-work
   └─ Updates Linear, cleans up

Authoritative References

  • {{PROJECT_REPO}}: Core agentic principles
  • AGENT_WORKFLOW_SOP.md: Full agent workflow documentation
  • CONTRIBUTING.md: Workflow requirements
  • linear-sop skill: Evidence templates for Linear

Anti-Patterns to Avoid

Anti-PatternWhy It's BadDo This Instead
Skip QAS reviewMiss commit message issuesAlways invoke QAS pre-merge
No evidence in LinearNo audit trailAttach evidence every phase
Ignore CI failuresBroken code reaches devFix in agent loop, don't skip
Force-push without checkMay lose teammate's changesUse --force-with-lease
Continue when blockedWaste time, no progressEscalate with context

© bybren-llc, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in .claude/skills/orchestration-patterns of bybren-llc/safe-agentic-workflow.

  • SKILL.md
  • README.md

Open the folder on GitHubat commit 26ca58b

Compare with similar skills

Orchestration Patterns next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Orchestration Patterns compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Orchestration Patterns this skillbybren-llc/safe-agentic-workflow423—~2kAutomated safety check: NotesMIT
Cursor Orchestratecursor/plugins10k—~1.1kAutomated safety check: PassNone
Babysitter Process Runnera5c-ai/babysitter1.8k1 repos~726Automated safety check: NotesMIT
Paseo Advisor Second Opiniongetpaseo/paseo20k1 repos~756Automated safety check: PassCustom licence
O2 Review Loopopenobserve/openobserve22k—~3.7kAutomated safety check: PassAGPL-3.0
Harness Agent Team Designerrevfactory/harness9.1k—~4.5kAutomated safety check: PassApache-2.0

Similar skills

  • Cursor Orchestrate

    cursor/plugins

    Official

    Splits a large goal into a tree of parallel Cursor cloud agents, with planners, workers and verifiers coordinated by a script and reporting through structured handoffs.

    10k GitHub stars~1.1k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Babysitter Process Runner

    a5c-ai/babysitter

    Execute via @babysitter. Use this skill when asked to babysit a task, do anything that is structured process-driven (even a loop) or whenever it is called…

    1.8k GitHub starsUsed in 1 repo~726 tokens
    Agent WorkflowsAuto-check: notes

  • Paseo Advisor Second Opinion

    getpaseo/paseo

    Launches one separate agent through Paseo to give a second opinion on the current task, with a self-contained briefing and no permission to edit files.

    20k GitHub starsUsed in 1 repo~756 tokens
    Agent WorkflowsAuto-check passed

  • O2 Review Loop

    openobserve/openobserve

    Splits a change into planner, coder and independent reviewer roles: you confirm a spec, a subagent implements it, and a separate reviewer checks each round's local WIP commit.

    22k GitHub stars~3.7k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Harness Agent Team Designer

    revfactory/harness

    Designs a project-specific agent harness: defines specialist agents, writes the skills they follow, picks an execution mode and model for each, and keeps the setup maintained.

    9.1k GitHub stars~4.5k tokensUpdated 11 days ago
    Agent WorkflowsAuto-check passed

  • ClawTeam Multi-Agent Swarm

    win4r/ClawTeam-OpenClaw

    Launches a swarm of specialist Hermes agents in git-worktree-isolated tmux windows with a kanban board and file-based inboxes, using built-in templates like hedge-fund and code-review.

    1.5k GitHub starsUsed in 1 repo~2.9k tokens
    Agent WorkflowsAuto-check passed

More from bybren-llc/safe-agentic-workflow

All 42 skills in this repo

  • Multi-Agent Coordination Template

    bybren-llc/safe-agentic-workflow

    Agent assignment matrix, blocker escalation, and TDM coordination patterns. Use when assigning work to specialist agents, managing blockers across agents…

    423 GitHub stars~1.2k tokensUpdated 2 mo ago
    Auto-check passed

  • API Route Patterns

    bybren-llc/safe-agentic-workflow

    API route implementation patterns with RLS, validation, and error handling. Use when creating API routes, implementing CRUD endpoints, adding server-side…

    423 GitHub stars~1.6k tokensUpdated 2 mo ago
    Auto-check passed

  • Technical Documentation Templates

    bybren-llc/safe-agentic-workflow

    Documentation templates for ADRs, runbooks, architecture docs, and knowledge transfer documents. Use when creating Architecture Decision Records, writing…

    423 GitHub stars~1.2k tokensUpdated 2 mo ago
    Auto-check passed

  • Deployment SOP Checklist

    bybren-llc/safe-agentic-workflow

    Deployment workflows, pre-deploy validation, smoke testing, and rollback procedures. Use when deploying to staging or production, running smoke tests…

    423 GitHub stars~950 tokensUpdated 2 mo ago
    Auto-check passed

  • Frontend Patterns Template

    bybren-llc/safe-agentic-workflow

    Frontend patterns for modern web frameworks, component libraries, auth flows, and analytics. Use when building UI components, creating pages, implementing…

    423 GitHub stars~2k tokensUpdated 2 mo ago
    Auto-check passed

  • Advanced Git Operations

    bybren-llc/safe-agentic-workflow

    Advanced git operations including rebase, bisect, cherry-pick, and conflict resolution. Use when rebasing feature branches, debugging with bisect…

    423 GitHub stars~1.6k tokensUpdated 2 mo ago
    Auto-check passed

Categories

Questions about Orchestration Patterns

What does Orchestration Patterns do?

Agentic orchestration patterns for long-running tasks. An agent skill from bybren-llc/safe-agentic-workflow. Orchestration Patterns is an agent skill from bybren-llc/safe-agentic-workflow. Agentic orchestration patterns for long-running tasks.

When should I use Orchestration Patterns?

Orchestration Patterns fits situations like: managing multi-step work; coordinating subagents; orchestrating PR workflows.

How do I install Orchestration Patterns in Claude Code?

Run `npx skills add bybren-llc/safe-agentic-workflow --skill orchestration-patterns -a claude-code`. Or copy the skill folder (.claude/skills/orchestration-patterns in bybren-llc/safe-agentic-workflow) into .claude/skills/orchestration-patterns in your project. Claude Code loads it when a task matches its description.

How do I install Orchestration Patterns in Codex?

Run `npx skills add bybren-llc/safe-agentic-workflow --skill orchestration-patterns -a codex`. Or copy the skill folder (.claude/skills/orchestration-patterns in bybren-llc/safe-agentic-workflow) into .agents/skills/orchestration-patterns in your project. Codex loads it when a task matches its description.

Can I use Orchestration Patterns in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add bybren-llc/safe-agentic-workflow --skill orchestration-patterns -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/orchestration-patterns, .gemini/skills/orchestration-patterns, .github/skills/orchestration-patterns and .opencode/skills/orchestration-patterns in your project.

What does Orchestration Patterns need to run?

Going by SKILL.md and its folder, Orchestration Patterns needs the command-line tools its instructions call (yarn). Its frontmatter pre-approves these tools: Read, Bash, Grep, Glob, Task.

Does Orchestration Patterns access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Orchestration Patterns safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Orchestration Patterns use?

Orchestration Patterns is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Orchestration Patterns use?

About 2k tokens (SKILL.md is roughly 7.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Orchestration Patterns?

Skills that share tags, products or a category with Orchestration Patterns: Cursor Orchestrate (cursor/plugins, 10k stars), Babysitter Process Runner (a5c-ai/babysitter, 1.8k stars), Paseo Advisor Second Opinion (getpaseo/paseo, 20k stars) and O2 Review Loop (openobserve/openobserve, 22k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Orchestration Patterns?

bybren-llc (a GitHub organization) maintains it in bybren-llc/safe-agentic-workflow, which has 423 GitHub stars. The repository holds 42 skills in this directory. The repository was last updated on July 20, 2026.

Source: bybren-llc/safe-agentic-workflow on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.