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 skills add HigorAlves/orc --skill explainergit 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/skills/higoralves/orc/explainer)<a href="https://agentmods.dev/skills/higoralves/orc/explainer"><img src="https://agentmods.dev/badge/skills/higoralves/orc/explainer/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/skills/higoralves/orc/explainer"><img src="https://agentmods.dev/badge/skills/higoralves/orc/explainer.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 | $0.00040 | $0.01181 |
| Opus 5.5 | $0.00016 | $0.00472 |
| Sonnet 5.5 | $0.00008 | $0.00236 |
| Haiku 4.5 | $0.00004 | $0.00118 |
Grade A, and why
explainer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explainer
Announce at start: "I'm using the explainer skill to build the narrated walkthrough."
Inputs: <qa-dir> with qa-manifest.json, the session's plan.md (optional), the target name + optional --base-url override for the demo pass (resolved inline per orc:qa-targets; never the resolved JSON), settings explainer_style (CLAUDE_PLUGIN_OPTION_EXPLAINER_STYLE, default isometric) and explainer_voice (CLAUDE_PLUGIN_OPTION_EXPLAINER_VOICE, default af_heart).
1. Toolchain
orc-explain setup (first run: npm install kokoro-js into the user cache; model downloads on first narration). command -v ffmpeg missing ⇒ stop with one line, no explainer. animate missing ⇒ say graphic segments will be plain title cards and continue.
2. Demo footage
If <qa-dir>/demo/ lacks a .webm per @golden scenario: ( cd <repo>/<dir> && ORC_TARGET_JSON="$(orc-targets resolve <name> [--base-url <override>])" ORC_PW_OUTPUT_DIR=<qa-dir>/pw-demo npx playwright test --project=demo ) (resolve stays inline — orc:qa-targets iron rule), then orc-qa-video plan --results <qa-dir>/pw-demo/results.json and copy each video to <qa-dir>/demo/<id>.webm.
3. Script → segments.json (schema: references/segments-schema.md)
Sources, in order: the plan's slice titles + acceptance (what was built), the manifest's acceptance rows (what was proven), git log --format=%s <base>..HEAD (what changed). Never the raw diff — the script describes behaviour, not code. Shape: s01 graphic (feature title + 2–3 lines), one clip segment per golden scenario (caption = the first AC title that scenario proves; narration = one sentence of what the viewer sees), sNN graphic outcome (criteria passed/total, notable skips). Narration lines ≤ 25 words, present tense, no file names. Total target ≤ 90 seconds. style from setting, voice from setting.
4. Explainer gate (soft-inward, header Explainer; guided/full pre-approve)
> **⛔ Gate — explainer**
>
> <N> segments, ~<seconds>s, style <style>, voice <voice>. Review the script before rendering.
preview = segments.json rendered as id · kind · caption/title · narration. Options: Render (Recommended) · Edit script (apply the user's wording changes, re-show) · Cancel.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago Changed · +1 lines · -20 tokens per session 995e7ef06e07
- 19d ago First seen · 40 lines · 60 tokens per session scan A 3a47c57615c0
explainer is a skill published in the GitHub repository HigorAlves/orc (7 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 1,181 once invoked, about $0.0002 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 skills, from other repositories
proof-e2e
Build E2E test specs for critical user journeys — Playwright or Cypress, page objects, setup/teardown, CI config. Use when asked to "write E2E tests", "end-to-end testing", "browser tests", "UI tests", or "Playwright tests".
proof-strategy
Produce a test strategy for a project or feature — risk map, test type decisions, coverage targets, CI config. Use when asked to "create test strategy", "what should we test", "testing plan", or "improve test coverage".
e2e
Orchestrates e2e testing: BDD scenarios, Playwright autotests. Triggers: e2e tests, BDD scenarios, write autotest.
e2e-panther-playwright
Write end-to-end tests with Symfony Panther 2.4 for browser automation or Playwright for complex scenarios.
functional-tests
Write functional tests for Symfony controllers and HTTP endpoints using WebTestCase, getContainer, loginUser, and DAMA rollback.
proof-recon
Testing reconnaissance — inventory all tests, frameworks, coverage, CI integration, and assess testing maturity for project takeover. Use when asked to "understand the tests", "testing assessment", "what's tested", or "test inventory".