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/orchestrate-plannpx skills add rossoctl/examples --skill orchestrate-plangit 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 | $0.01138 |
| Opus 5 | $0.00013 | $0.00569 |
| Sonnet 5 | $0.00005 | $0.00228 |
| Haiku 4.5 | $0.00003 | $0.00114 |
Grade A, and why
orchestrate:plan 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
flowchart TD
START(["/orchestrate:plan"]) --> READ["Read scan report"]:::orch
READ --> PRESENT["Present findings"]:::orch
PRESENT --> BRAINSTORM["Brainstorm with developer"]:::orch
BRAINSTORM --> SELECT["Select applicable phases"]:::orch
SELECT --> SIZE["Size PRs (600-700 lines)"]:::orch
SIZE --> WRITE["Write plan document"]:::orch
WRITE --> DONE([Plan complete])
classDef orch fill:#FF9800,stroke:#333,color:white
Follow this diagram as the workflow.
Orchestrate: Plan
Take the scan report and turn it into a concrete phased enhancement plan. This is Phase 1 — interactive brainstorming with the developer, no PRs.
When to Use
- After
orchestrate:scanhas produced a scan report - Before starting any PR-producing phase
Prerequisites
Scan report must exist:
cat /tmp/rossoctl/orchestrate/<target>/scan-report.md
Planning Process
1. Read the scan report
Review the Gap Summary and Recommended Phases sections.
2. Present findings to developer
Summarize the key gaps in plain language. Use AskUserQuestion to confirm understanding and gather context about the repo's priorities.
3. Brainstorm which phases apply
Not all repos need all phases. Use AskUserQuestion to decide:
| Gap Found | Phase | Default |
|---|---|---|
| No pre-commit config | orchestrate:precommit |
Always (foundation) |
| No/incomplete CI workflows or security scanning | orchestrate:ci |
Yes if missing |
| No/few tests (<5 test files) | orchestrate:tests |
Yes if low coverage |
| No CODEOWNERS/SECURITY.md/LICENSE | orchestrate:security |
Recommended |
No .claude/skills/ directory |
orchestrate:replicate |
Always (last phase) |
4. Determine phase order
Default order: precommit → tests → ci → security → replicate
Tests come before CI (so CI can run them) and before security (so code refactoring for security fixes has test coverage as a safety net). Pre-commit is always first (it validates subsequent PRs). Replicate is always last.
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 · 149 lines · 26 tokens per session scan A 604d10973f2f
orchestrate:plan 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 1,138 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.