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 commands/mbruhler/claude-orchestration/pullgit clone --depth 1 https://github.com/mbruhler/claude-orchestrationWhat 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 | $0.00012 | $0.00427 |
| Opus 5 | $0.00006 | $0.00214 |
| Sonnet 5 | $0.00002 | $0.00085 |
| Haiku 4.5 | $0.00001 | $0.00043 |
Grade A, and why
pull scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s https://raw.githubusercontent.com/mbruhler/claude-orchestration/main/registry/index.json What it actually says
Pulling Workflows
Downloads a workflow from the community registry or directly from a GitHub repository and saves it to your local workspace.
Arguments: {{ARGS}}
The workflow identifier to pull. This can be:
- A name from the official registry (e.g.
tdd-autopilot) - A direct GitHub path (e.g.
username/repo/path/to/workflow.flow)
Execution Process
Phase 1: Determine Source
Check the argument to see if it's a direct GitHub path (contains a /) or a registry name (no /).
Phase 2: Fetch Registry (If applicable)
If it's a registry name, fetch the official registry index using bash:
curl -s https://raw.githubusercontent.com/mbruhler/claude-orchestration/main/registry/index.json
Parse the JSON and find the URL for the requested workflow. If not found, show an error and list available workflows.
Phase 3: Construct Raw URL (If direct GitHub path)
If the user provided username/repo/workflow.flow, convert it to a raw GitHub URL:
https://raw.githubusercontent.com/username/repo/main/workflow.flow
(You may need to ask the user if the branch is main or master if the first attempt fails).
Phase 4: Download the Workflow
Use curl or wget to download the file content.
Save the downloaded content into the ./examples/ directory in the current working directory, using the workflow's filename.
mkdir -p ./examples
curl -sL "<URL>" -o "./examples/<workflow-name>.flow"
Phase 5: Confirm
Display a success message to the user:
✅ Successfully pulled workflow: <workflow-name>
Saved to: ./examples/<workflow-name>.flow
To run it, type:
/orchestration:run ./examples/<workflow-name>.flow
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.
- 2d ago First seen · 50 lines · 12 tokens per session scan A e59b6c02747e
pull is a command published in the GitHub repository mbruhler/claude-orchestration (218 stars, last pushed 3mo ago), licensed MIT. It adds 12 tokens to every session and 427 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.