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/boardkit/orchestrator/setup-orchestratorgit clone --depth 1 https://github.com/BoardKit/orchestratorWhat 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 | $0.00019 | $0.06023 |
| Opus 5 | $0.00010 | $0.03011 |
| Sonnet 5 | $0.00004 | $0.01205 |
| Haiku 4.5 | $0.00002 | $0.00602 |
Grade B, and why
setup-orchestrator scanned grade B 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
repo/.claude/settings.json -> ../../orchestrator/shared/settings/[repo-name]/settings.json How it starts
The opening of the file, as written. The whole thing — 920 lines — stays where its author put it; the contents beside it link to each section on GitHub.
⚠️ IMPORTANT: This command should ONLY be run from the orchestrator repository, not from application repositories.
Role: Interactive orchestrator configuration specialist
Mission: Guide users through first-time orchestrator setup, collecting organization details, discovering repositories, creating symlinks, and generating all necessary documentation.
Core Responsibilities
-
Collect Organization Information
- Organization name
- Primary tech stacks used
- Number of repositories to manage
-
Discover and Configure Repositories
- For each repository:
- Repository name
- Absolute path on filesystem
- Repository type (frontend, backend, fullstack, ML, etc.)
- Primary tech stack
- For each repository:
-
Create Symlink Structure
- Create directory-level symlinks for agents (all repos get access to global/ agents)
- Create directory symlinks for skills, guidelines, hooks, and commands
- Each repo gets symlinks to global resources + their repo-specific resources
-
Generate Repository-Specific Skills
- Create skills that auto-trigger for each repo's tech stack
- Update skill-rules.json with appropriate patterns
-
Generate Guidelines
- Create architectural-principles.md
- Create error-handling.md with repo-specific patterns
- Create testing-standards.md with repo-specific frameworks
- Optionally create cross-repo-patterns.md
- Optionally create database documentation (if applicable)
-
Update Documentation
- Customize CLAUDE.md with repo-specific information
- Update README.md with organization details
- Create SETUP_CONFIG.json for future reference
Setup Workflow
Phase 1: Information Gathering
Step 1: Welcome and Prerequisites Check
Display:
- Welcome message
- Prerequisites (git, filesystem access, symlink support)
- What will be configured
Check:
- Current directory is orchestrator root
- shared/ directory exists
- No existing SETUP_CONFIG.json (not already configured)
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 · 920 lines · 19 tokens per session scan B 669244c49878
setup-orchestrator is a command published in the GitHub repository BoardKit/orchestrator (37 stars, last pushed 5mo ago), licensed MIT. It adds 19 tokens to every session and 6,023 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
project
Manage projects: register repos, inspect, configure per-project settings, and remove.
review
Manage AO code reviews of a worker's PR.
send
Send a message to a running agent session. Use this to correct or direct a live agent mid-stream without killing and respawning it.
apply-self-review
Apply the approved improvements from the latest memory-self-review PROPOSAL. Auto-applies the safe, reversible doc/memory edits (with backups); queues code/config/rule-rewrite edits for an explicit go. Never commits or pushes.
publish-core
Trigger the canonical publish pipelines in this repo.
init
Scaffold the full, writable Cantos system into the current project (CLAUDE.md, assistants, workflows, references, self-improvement spine), then run first-run setup.