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/rossoctl/examples/orchestratenpx skills add rossoctl/examples --skill orchestrategit clone --depth 1 https://github.com/rossoctl/examplesWhat 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 | $0.00026 | $0.01688 |
| Opus 5 | $0.00013 | $0.00844 |
| Sonnet 5 | $0.00005 | $0.00338 |
| Haiku 4.5 | $0.00003 | $0.00169 |
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 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
flowchart TD
START(["/orchestrate"]) --> HAS_SCAN{Has scan report?}
HAS_SCAN -->|No| SCAN["orchestrate:scan"]:::orch
SCAN --> PLAN["orchestrate:plan"]:::orch
HAS_SCAN -->|Yes| HAS_PLAN{Has plan?}
HAS_PLAN -->|No| PLAN
HAS_PLAN -->|Yes| NEXT_PHASE{Next phase?}
NEXT_PHASE -->|Phase 2| PRECOMMIT["orchestrate:precommit<br/>PR #1"]:::orch
NEXT_PHASE -->|Phase 3| TESTS["orchestrate:tests<br/>PR #2"]:::orch
NEXT_PHASE -->|Phase 4| CI["orchestrate:ci<br/>PR #3"]:::orch
NEXT_PHASE -->|Phase 5| SECURITY["orchestrate:security<br/>PR #4"]:::orch
NEXT_PHASE -->|Phase 6| REPLICATE["orchestrate:replicate<br/>PR #5"]:::orch
NEXT_PHASE -->|Phase 7| REVIEW["orchestrate:review"]:::orch
PRECOMMIT --> TESTS
TESTS --> CI
CI --> SECURITY
SECURITY --> REPLICATE
REPLICATE --> REVIEW
REVIEW --> DONE([All phases complete])
classDef orch fill:#FF9800,stroke:#333,color:white
classDef check fill:#FFC107,stroke:#333,color:black
class HAS_SCAN,HAS_PLAN,NEXT_PHASE check
Follow this diagram as the workflow.
Orchestrate Skills
Enhance any repository with CI, tests, skills, and security through a series of phased PRs. Each phase produces a focused, reviewable PR of 600-700 lines.
Entry Point Routing
When /orchestrate is invoked, determine the action:
What was provided?
|
+-- /orchestrate <repo-path>
| New target. Clone or locate the repo, then start from scan.
| Example: /orchestrate .repos/my-service
|
+-- /orchestrate <phase>
| Jump to a specific phase. Requires scan + plan to already exist.
| Example: /orchestrate ci
|
+-- /orchestrate status
Show current orchestration state for all tracked targets.
Route logic
/orchestrate <repo-path>-- If the path points to a git repository, derive the target name from the directory basename. Check/tmp/rossoctl/orchestrate/<target>/for existing state. If no scan report exists, invokeorchestrate:scan. If scan exists but no plan, invokeorchestrate:plan. If both exist, determine the next incomplete phase and invoke it.
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 · 150 lines · 26 tokens per session scan A 62c23bfa1acb
orchestrate is a skill published in the GitHub repository rossoctl/examples (11 stars, last pushed 4d ago), licensed Apache-2.0. It adds 26 tokens to every session and 1,688 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
importing-a-codebase
Use when the repo holds real source code but no specs: the existing-codebase branch of setting-up-a-project, normally reached via that dispatcher, directly only when the situation is unmistakable. Not for empty workspaces (starting-a-new-project) or feature work in a specced project (brainstorming).
starting-a-new-project
Use when the workspace is empty — no code yet — and the user brings a raw idea: the brand-new branch of setting-up-a-project, normally reached via that dispatcher, directly only when the situation is unmistakable. Not for features in an existing project — use brainstorming instead.
todos
This chat has a shared, live TODO plan — your tasks for the conversation, which the user also edits. Read this skill and reach for the todo tools whenever a request takes more than a couple of steps. It covers the plan model (group = task, items = its steps; loose items are the user's lane), how to work it: propose…
writing-workflow-skills
Use when adding a new workflow skill to pi-thinkrail-workflow, changing an existing workflow skill's role, trigger, handoff, or structure, or checking a workflow skill against the workflow system's rules. Not for authoring general-purpose skills outside this package.
brainstorming
Use this BEFORE any creative or feature work: building a new feature, adding functionality, changing behavior, or making a nontrivial design decision. Turns the user's request into a validated design — recorded as a spec-graph task-spec — before any implementation. Do not skip this because a change looks small.
reviewing-changes
Use when a review package asks you to review a plan step's change set (todo.startReview): you are the REVIEWER, not the author. How to judge an agent-written diff, file findings with addreviewcomment, and settle with exactly one reviewverdict.