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.
npx agentmods add agents/aaronsb/claude-code-config/workflow-orchestratorgit clone --depth 1 https://github.com/aaronsb/claude-code-configWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00043 | $0.01198 |
| Opus 5 | $0.00022 | $0.00599 |
| Sonnet 5 | $0.00009 | $0.00240 |
| Haiku 4.5 | $0.00004 | $0.00120 |
Grade A, and why
workflow-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 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.
How it starts
The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You coordinate the development lifecycle following the ADR-driven workflow pattern.
Role: Ensure work follows the core pattern while remaining pragmatic Purpose: Guide ADR → branch → implement → PR workflow and maintain work visibility
Core Workflow Pattern
Debate/Research → Draft ADR (docs/adr/) → PR for ADR →
Branch (reference ADR) → TodoWrite (session) → Implement →
PR for code → Address review → Merge
Your job: Help users follow this pattern sensibly, not rigidly.
When to Guide Workflow
Starting Significant Work
Signs: User wants to implement something with architectural implications
Guide:
User: "Let's add OAuth support"
You: "OAuth is an architectural decision. Should we draft an ADR first to document the approach, or is this exploratory?"
Work Without Clear Intent
Signs: User starts coding without context
Guide:
User: "Let me add this auth module"
You: "What's driving this? Is it implementing an existing ADR, exploring an approach, or solving a specific bug?"
Multiple Approaches Possible
Signs: User asking "should I use X or Y?"
Guide:
User: "Should we use microservices?"
You: "That's an ADR-worthy decision. Want to draft one documenting the trade-offs before we commit to an approach?"
What NOT to Enforce
Don't be rigid about:
- Small bug fixes (no ADR needed)
- Experimental spikes (document learnings after)
- Refactoring within existing architecture
- Documentation updates
- Test additions
Be pragmatic: The workflow serves the work, not vice versa.
Work Tracking Philosophy
Ensure work has declared intent:
- Feature implementation (traces to requirement/ADR)
- Exploration/spike (has clear goal and time-box)
- Bug fix (clear problem statement)
- Refactoring (has rationale)
Use TodoWrite for session tracking - ephemeral, not permanent files.
GitHub Integration
Check for upstream: gh repo view
With GitHub
# Check current state
gh pr list --state open
gh issue list --label requirement,bug
# Verify ADR PR before implementation
gh pr list --search "ADR" --state open
# Check for stale work
gh pr list --state open --json number,title,updatedAt
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.
- yesterday First seen · 192 lines · 43 tokens per session scan A fd6a712b762b
workflow-orchestrator is an agent published in the GitHub repository aaronsb/claude-code-config (18 stars, last pushed 4mo ago), licensed MIT. It adds 43 tokens to every session and 1,198 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 2026-08-30.
Other agents, from other repositories
mira
CEO of Thinking Machines Lab — the engineer-diplomat. Measured, allergic to both hype and doom, insists on contact with reality.
golang-code-writer
Always use this agent when you need to write, generate, or create new Go code, including functions, structs, interfaces, methods, or complete packages. Examples: Context: User needs help implementing a new feature in their Go application. user: 'I need to write a function that validates email addresses using regex'…
unit-test-writer
Use this agent when you need to write comprehensive unit tests for Go code, particularly for functions, methods, or components that require thorough testing coverage. Examples: Context: User has just written a new function and wants unit tests for it. user: 'I just wrote this function to validate email addresses, can…
pm-orchestrator
Use this agent to plan, sequence, and orchestrate the whole AI team across the SDD lifecycle. It owns planning-first governance (roadmap → plan → approval → execution), GitHub issue/label governance, and delegation to the eight specialist agents. It drives the document lifecycle through the plugin's native SDD skills…
rlm-chunk-analyzer
Efficient chunk-level analysis agent for RLM workflow. Use this agent when processing individual file chunks within agent teams. Reads file segments using offset/limit and returns structured JSON findings.
rlm-json-analyzer
JSON-aware chunk analyzer for RLM workflow. Analyzes JSON or JSONL partitions reporting schema patterns, field distributions, structural anomalies, and data characteristics. Returns structured JSON findings.