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/jdanigo/hydraia/adrnpx skills add jdanigo/hydraia --skill adrgit 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/skills/jdanigo/hydraia/adr)<a href="https://agentmods.dev/skills/jdanigo/hydraia/adr"><img src="https://agentmods.dev/badge/skills/jdanigo/hydraia/adr.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 | $0.00055 | $0.00419 |
| Opus 5 | $0.00028 | $0.00210 |
| Sonnet 5 | $0.00011 | $0.00084 |
| Haiku 4.5 | $0.00006 | $0.00042 |
Grade A, and why
adr 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 4d 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.
What it actually says
ADR — Architecture Decision Records (MADR-lite)
One file per decision: docs/hydraia/adr/NNNN-<slug>.md, zero-padded, monotonic (0001-..., 0002-...). Find the next number with ls docs/hydraia/adr/ | sort | tail -1.
When to write one (all it takes is ONE of these)
- Expensive to reverse (data store, auth model, hosting, framework).
- Affects multiple components or teams.
- A plausible alternative was seriously considered and rejected.
When NONE hold → no ADR. ADR spam buries the decisions that matter.
Template
# NNNN — <decision title>
**Status:** proposed | accepted | superseded by NNNN
**Date:** YYYY-MM-DD
## Context
<the forces: requirements, constraints, and any assumption made because
the human could not answer — stated as an assumption with its revisit
trigger>
## Decision
<what was decided, in one or two sentences, active voice>
## Alternatives considered
- <alternative> — rejected because <reason>
## Consequences
- Good: <what this buys>
- Bad: <what this costs — every decision costs something; empty is a smell>
Lifecycle rules
- Write at decision time (Phase 2 / greenfield step 5), commit with the spec.
- Supersede, never rewrite: a change of mind = NEW ADR + flip the old one's Status to
superseded by NNNN. History stays honest. - The Phase 2 spec references ADRs by number; reviewers check code against accepted ADRs.
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.
- 4d ago First seen · 45 lines · 55 tokens per session scan A 2698dff50067
adr is a skill published in the GitHub repository jdanigo/hydraia (8 stars, last pushed 15d ago), licensed MIT. It adds 55 tokens to every session and 419 once invoked, about $0.0003 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 skills, from other repositories
frame-macos-notification
拟真 macOS 通知 banner + app icon + 标题正文, 适合 video overlay / 产品发布预告.
prototype-web
可点击的功能性 Web 原型, 含导航、英雄区、特性区、CTA.
waitlist-page
【模板: 等候名单页 / Waitlist】 【意图】为新产品 / 早鸟内测做一张极简等候页。 【布局】.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
deck-pitch
10 页融资 deck, 白底 + 蓝紫渐变 hero, traction 柱状, $X.XM ask.
argent-tv-interact
Control and inspect TV apps via argent — Apple TV (tvOS), Android TV (leanback), and Amazon Fire TV (Vega). Boot the target, read focus, navigate with the D-pad remote, type, screenshot, and on Vega debug the JS runtime (evaluate, console logs, network inspector). Use when a task targets a TV (runtimeKind "tv", or…