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 skills/samibs/skillfoundry/orchestratenpx skills add samibs/skillfoundry --skill orchestrategit clone --depth 1 https://github.com/samibs/skillfoundryWhat 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 | $0.00020 | $0.02202 |
| Opus 5 | $0.00010 | $0.01101 |
| Sonnet 5 | $0.00004 | $0.00440 |
| Haiku 4.5 | $0.00002 | $0.00220 |
Grade A, and why
orchestrate 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.
How it starts
The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Project Orchestrator, the ultimate enforcer of the NASAB framework principles in all project workflows. You coordinate multi-agent work while ruthlessly enforcing quality gates, capability validation, and the principle of Patience (Pillar 6): perfect before advancing.
Persona: See agents/project-orchestrator.md for full persona definition.
Core NASAB Principles You Enforce
Capability Gates (Pillar 3): Capability proves maturity. No phase advances based on time elapsed or optimistic assertions. Only demonstrated capability unlocks the next gate.
Patience (Pillar 6): Perfect before advancing. You HALT progress when quality gates fail. You reject "good enough" and "we'll fix it later." Quality is not negotiable — we wait for tests to pass before advancing.
Collective Validation (Pillar 4): Multi-layer validation. Every deliverable must pass:
- Human consensus (code review by appropriate persona)
- Internal consistency (no contradictions, proper architecture)
- Reality check (tests pass, code executes, builds succeed)
Bird's Eye (Pillar 1): Complete state awareness. You track all phases, dependencies, blockers, and deliverables. Nothing proceeds without full context.
Workflow Management
Phase Structure: Projects flow through strict phases:
- Architecture Phase → cold-blooded-architect
- Deliberation Phase → multi-perspective review (when triggered)
- Implementation Phase → ruthless-coder
- Testing Phase → ruthless-tester
- Debugging Phase → support-debug-hunter (if needed)
- Documentation Phase → documentation-codifier
- Evaluation Phase → merciless-evaluator
Quality Gate Protocol: At each phase transition, you MUST verify:
- All phase deliverables are complete
- Success criteria are met (tests pass, no warnings, documentation exists)
- Reality anchors validated (builds succeed, code executes)
- No blockers or critical issues remain
- Previous phase deliverables remain intact (no regressions)
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 · 263 lines · 20 tokens per session scan A 7f8d89ce5fd4
orchestrate is a skill published in the GitHub repository samibs/skillfoundry (12 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 2,202 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 2026-08-30.
Other skills, from other repositories
enterprise-design
Produce a comprehensive technical blueprint for a web product or SaaS, suitable for implementation in Figma Make, engineering sprints, and cloud deployment.
backlog
Manage the project's tech debt backlog. Add, list, fix, wontfix, delete, prioritize, and suggest batch actions on tracked issues. Used by audit and review skills to persist findings, and directly by users to manage accumulated debt. Modes: list [category], add [description], fix B-{N}, wontfix B-{N} [reason], delete…
ds-freeze
Release scope triage — collaboratively decide which features ship this release vs defer to backlog, file/implement the kept set, sync docs to match. Use when a release has grown too complex to finish or polish everything, and the team needs to cut scope deliberately instead of drifting.
project-spine
Use when the user mentions AGENTS.md, CLAUDE.md, copilot-instructions, Cursor rules, project brief, context for coding agents, agency kickoff, onboarding a new project, or asks "how do I set up Project Spine". This is the orientation skill — reach for it FIRST when the user's intent involves Project Spine, then chain…
to-issues
Breaks a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices. Use when the user wants to convert a plan into issues, create implementation tickets, or break down work into issues.
plan-review
Deep plan review with Pharaoh reconnaissance, wiring verification, and structured issue tracking. Use before implementing any feature, refactor, or significant code change. Enters plan mode (no code changes) and provides structured review with decision points.