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/jdanigo/hydraiaWrote 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/jdanigo/hydraia/explainme)<a href="https://agentmods.dev/commands/jdanigo/hydraia/explainme"><img src="https://agentmods.dev/badge/commands/jdanigo/hydraia/explainme/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/jdanigo/hydraia/explainme"><img src="https://agentmods.dev/badge/commands/jdanigo/hydraia/explainme.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 | $0.00041 | $0.00516 |
| Opus 5 | $0.00020 | $0.00258 |
| Sonnet 5 | $0.00008 | $0.00103 |
| Haiku 4.5 | $0.00004 | $0.00052 |
Grade A, and why
explainme 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 today.
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.
What it actually says
Invoke the explainme skill to produce a visual, verifiable explanation of the code in question. Follow the skill's Hydraia grounding first:
- Resolve the scope from
$ARGUMENTS(a subsystem, a path, a PR diff, or a "how does X work" question). Default to the current repo's headline subsystem if unscoped. - Query codegraph for the real structure — components/modules, call edges, entry points, storage/transports, blast radius. This is the topology source; do not guess it.
- Pick the diagram type that fits (architecture / workflow / sequence / dataflow /
lifecycle) —
node skills/explainme/bin/archify.mjs guide "<scenario>" --jsonif unsure. - Author the typed IR from the verified codegraph nodes/edges; set
SRCsource-evidence from real file:line so nodes are click-through. Attach up to ~5 guided-walkthroughviewschapters framing the onboarding path (request path / auth flow / data lineage / lifecycle). - Validate then deliver, running the CLI from the skill directory:
cd skills/explainme && node bin/archify.mjs validate <type> <in.json> --quality showcase --jsonthennode bin/archify.mjs deliver <type> <in.json> <out.html> --json. Consume thediagnostics[]repair receipts in a bounded loop (change only the diagnosed subject, at most one geometry control per repair, stop after two non-improving rounds). - Write the artifact under the resolved artifacts base (
<base>/explain/<slug>.html) and hand the user the path. Do NOT run the full build pipeline — this is an explanation artifact, not a code change; no spec/plan/review gates apply.
Delegate the authoring to the explainme agent (Sonnet) when available; the deterministic
CLI carries the correctness. Requires Node ≥ 18 (see /hydraia:doctor).
Request: $ARGUMENTS
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.
- today First seen · 32 lines · 41 tokens per session scan A 01287df3cb5d
explainme is a command published in the GitHub repository jdanigo/hydraia (8 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 516 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 2026-09-12.
Other commands, from other repositories
design-tutorial
Interactive guided tour of Naksha — learn commands through real exercises, discover workflows, and get oriented in under 10 minutes.
ux-onboarding
Get familiar with a project's UX/design choices and patterns — a guided, part-by-part walkthrough that sends you to read the real code, checks your understanding with questions, and has you reimplement a small recent change.
octo-design-ui-ux
Design UI/UX systems with style guides, palettes, typography, and component specs.
verify
Fidelity check — rebuild a page from the extracted tokens, pixel-diff it against the live site, and score how faithfully the tokens capture the design.
critique-screen
Run all seven visual critiques on a screen and output a prioritised fix list.
design-onboarding
Design a first-run experience end to end — activation path, progressive disclosure, and time to first value.