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/higoralves/orc/plangit clone --depth 1 https://github.com/HigorAlves/orcWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/higoralves/orc/plan)<a href="https://agentmods.dev/commands/higoralves/orc/plan"><img src="https://agentmods.dev/badge/commands/higoralves/orc/plan.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00042 | $0.02826 |
| Opus 5 | $0.00021 | $0.01413 |
| Sonnet 5 | $0.00008 | $0.00565 |
| Haiku 4.5 | $0.00004 | $0.00283 |
Grade A, and why
plan scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/orc:plan
Turn a feature or refactor request into a written, TDD-shaped implementation plan. Persist it to .orc/<branch>/files/plan.md so the work can pause and resume.
Arguments
-
--auto[=guided|full]— autopilot level for this run (overridesinteraction_policy; taxonomy inorc:using-orc). Soft-inward gates consult the resolved policy —guidedauto-advances mechanical confirms with a printed one-liner;fullpre-approves them from settled decisions (orc:state-protocol), stopping only on escalation-only conditions. Hard-outward gates are unaffected at every level. -
--grill— after drafting the plan, invokeorc:grill-meto stress-test the design before committing. -
--issues— after the plan is approved, runorc:to-issuesto break it into independently grabbable issues. -
--jira <KEY>— link a Jira ticket key (e.g.PROJ-123) to this session silently. Suppresses the Phase 1 link prompt. Validate against^[A-Z][A-Z0-9_]*-\d+$. -
--repos <list>,--repo <name>,--all-repos,--this-repo— workspace-mode repo selection. Seeorc:workspace-modefor precedence. -
The feature description is the rest of the argument string.
Workflow
Phase 0 — Detect PRD-shaped input (optional)
If the feature description is long-form, references a Jira ticket / linked doc, or reads more like a brief than a settled spec — dispatch the orc-prd-analyzer subagent via Task first. Pass it the input + the URL if there is one. The agent returns a structured analysis (extracted goals, ambiguities, P0/P1/P2 clarifying questions, recommendation).
After the analyzer returns, print the Gate headline (**⛔ Gate — PRD analysis**, one line on P0/P1/P2 counts, per orc:callouts), then AskUserQuestion:
- "Proceed to plan — questions are P1/P2 only"
- "Hold — answer P0 questions with PM first" (exit; don't waste planning effort)
- "Run
/orc:rfcfirst — design space needs RFC treatment"
If the input is short and clear, skip Phase 0 and go straight to Phase 1.
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.
- 3d ago First seen · 149 lines · 42 tokens per session scan A b20a14978c9d
plan is a command published in the GitHub repository HigorAlves/orc (6 stars, last pushed 7d ago), licensed MIT. It adds 42 tokens to every session and 2,826 once invoked, about $0.0002 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 2026-08-31.
Other commands, from other repositories
codegen
TDD-first codegen for a scv/promote/ / plan. Verifies TESTS fail first (Red), then iteratively writes the minimum code to pass each case (Green). Hands off archive/PR/regression to /scv:work. Use whenever the user wants a plan implemented test-first — 'TDD', 'tests first', 'red-green' — not only when they type…
go-test
Go TDD workflow with table-driven tests.
pm-auto-design2dev
設計レビューから実装完了まで完全自動化（設計レビュー→作業計画→TDD実装）.
tdd
强制执行测试驱动开发工作流。首先搭建接口，生成测试，然后从实现能通过测试的最小代码。确保 80%+ 的覆盖率。.
t800-onboard
Для чата с новичками. Показывает, что настроено в Cursor (global + local), и что умеет отдел T-800.
triage
Triage review findings one by one — present pending TODOs for user decision (approve, skip, modify).