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.
git 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/explain)<a href="https://agentmods.dev/commands/higoralves/orc/explain"><img src="https://agentmods.dev/badge/commands/higoralves/orc/explain/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/higoralves/orc/explain"><img src="https://agentmods.dev/badge/commands/higoralves/orc/explain.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00072 | $0.00877 |
| Opus 5.5 | $0.00029 | $0.00351 |
| Sonnet 5.5 | $0.00014 | $0.00175 |
| Haiku 4.5 | $0.00007 | $0.00088 |
Grade A, and why
explain scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/orc:explain
Turn a QA packet into a short narrated walkthrough of what was built and proven: demo footage of the golden path, motion-graphic title/callout/outcome segments, one voice track. Everything renders locally (kokoro-js, ffmpeg, optional animate plugin). Nothing is uploaded without the evidence-publish gates.
Arguments
--qa-dir <dir>— packet to explain. Default: the active session's${ORC_STATE_DIR}/<sanitized-branch>/files/qa/; else the newest.orc/evidence/*/packet; else ask.--target <name>— target for the demo pass when the packet has nodemo/clips (orc:qa-targets); default: the session's settledtarget.--style <s>— animate style (cut-paper|crosshatch|riso|sketchbook|math|pixel|isometric); default userConfigexplainer_style.--voice <v>— kokoro voice id; default userConfigexplainer_voice(af_heart;pf_dorafor pt-BR).--auto[=guided|full]— autopilot (orc:gates§6). Pre-approves the Explainer gate; delivery gates always ask.
Workflow
Phase 0 — Context
!orc-workspace-detect --banner
Resolve the packet dir (above). qa-manifest.json missing ⇒ stop: 🛑 No QA packet — run /orc:qa first.
Phase 1 — Build
Invoke orc:explainer with the packet dir, the plan path when the session has one, the target name + override (only if the demo pass is needed; the skill resolves credentials inline, never as a standalone command), style, voice. It runs the demo pass if needed, writes explain/segments.json, runs the Explainer gate, narrates, authors the animate scenes (when animate is installed), renders explainer-<branch>.mp4, and updates the manifest + steps.md.
Phase 2 — Deliver
Invoke orc:evidence-publish with qaDir, the manifest verdict, and explainerFile. Its questions (Jira upload / private Artifact / PR comment) are hard-outward — always asked. Keep-local is the default.
Phase 3 — Record
Session present ⇒ orc-state digest write - with Explainer: explainer-<branch>.mp4 (<seconds>s) and append ## Explainer — <ISO> to progress.md.
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.
- 9d ago First seen · 59 lines · 72 tokens per session scan A 718c6002b6c5
explain is a command published in the GitHub repository HigorAlves/orc (6 stars, last pushed 8d ago), licensed MIT. It adds 72 tokens to every session and 877 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-08.
Other commands, from other repositories
verify-work
Validate built features through conversational UAT.
e2e
Generate and run E2E tests with Playwright.
test-browser
Run browser tests on pages affected by current PR or branch.
test-suite
Run comprehensive test suite with coverage analysis.
health-check
Perform a comprehensive, read-only end-to-end review of any portfolio app across three layers — Frontend (E2E), Database integrity, and Audit Log & User Activity — and produce a structured, observations-only report. Optionally, on explicit opt-in, generate (never apply) the infrastructure provisions needed so future…
gba-test
$ARGUMENTS: test mode — game profile defines available modes (e.g., smoke, gameplay, save, stress, full, ai, battle, nav, custom ).