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/rchase999/aidd/decision-gatenpx skills add rchase999/aidd --skill decision-gategit clone --depth 1 https://github.com/rchase999/aiddWrote 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/rchase999/aidd/decision-gate)<a href="https://agentmods.dev/skills/rchase999/aidd/decision-gate"><img src="https://agentmods.dev/badge/skills/rchase999/aidd/decision-gate.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 | $0.00051 | $0.01803 |
| Opus 5 | $0.00026 | $0.00901 |
| Sonnet 5 | $0.00010 | $0.00361 |
| Haiku 4.5 | $0.00005 | $0.00180 |
Grade A, and why
decision-gate 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 5d 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The decision gate
A browser page cannot hand data to a terminal agent. So the gate ships its own server: Claude launches gate-server.mjs in the background, the user chooses in a real browser, and the server writes the contract and exits. That exit is how Claude learns the gate passed.
options.json ──► gate-server ──► themed page in browser
▲ │
└──── POST /submit ◄─┘ (only on Submit)
│
writes decisions.md + decisions.json
sets phase = execute, exits 0
options.json
{
"project": { "name": "…", "tagline": "…" },
// Brownfield only — what the existing codebase already fixes.
// Rendered as a panel above the tabs and copied into the contract.
"context": {
"mode": "brownfield",
"summary": "two sentences a newcomer could act on",
"stack": [
{ "name": "Django 5.0", "detail": "DRF for the API", "evidence": "pyproject.toml" }
],
"constraints": ["Python 3.11 — pinned by the deployment image"],
"doNotBreak": ["The nightly invoicing job — it is the revenue path"]
},
"theme": {
"palette": { "bg","surface","surface2","line","ink","muted",
"accent","accent2","apply","infer","innovate" },
"fontDisplay": "\"Fraunces\", Georgia, serif",
"fontBody": "\"Inter\", system-ui, sans-serif",
"fontImport": "https://fonts.googleapis.com/css2?…",
"heroTexture": "radial-gradient(…)",
"heroSvg": "<svg …>…</svg>", // inline, authored locally
"heroImage": "assets/hero.webp" // relative to .aidd/02-research/
},
"segments": [
{
"id": "kebab-slug",
"title": "Runtime & Language",
"summary": "what this decision governs and what it locks in downstream",
"question": "the question to hold in mind while choosing", // optional
// Already settled by the existing codebase. Renders read-only: no stance
// buttons, no defer, excluded from the submit requirement, reaches the
// contract as LOCKED. Requires lockedReason. Show exactly one option —
// the thing that is actually in place.
"locked": true,
"lockedReason": "Celery already runs nightly invoicing (app/tasks/invoicing.py)",
"options": [
{
"id": "kebab-slug",
"name": "SvelteKit on Node",
"kind": "Full-stack JS", // optional
"maturity": "stable", // optional
"recommended": true, // max one per segment
"blurb": "one sentence",
"pros": ["…"], // required, non-empty
"cons": ["…"], // required, non-empty
"sources": [{ "title": "…", "url": "https://…", "note": "…" }]
}
]
}
]
}
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.
- 5d ago First seen · 162 lines · 51 tokens per session scan A d5e093daad42
decision-gate is a skill published in the GitHub repository rchase999/aidd (2 stars, last pushed 26d ago), licensed MIT. It adds 51 tokens to every session and 1,803 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
broken-link-checker
Scans a website to find broken links (404s, 500s). Crawls internal pages, identifies broken outbound links, and reports source pages for easy fixing. Use this when the user asks to "check for broken links", "find 404s", "audit my links", or "is my site healthy".
preview-screens
Use when the user wants to preview generated screens in a browser without starting Metro / a simulator — for example after /create-mobile-app finishes or after /edit-app regenerates a screen.
qa
Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).
moai-platform-chrome-extension
Chrome Extension Manifest V3 development specialist covering service workers, content scripts, message passing, chrome. APIs, side panel, declarativeNetRequest, and Chrome Web Store publishing. Use when building browser extensions.
11-browser-qa
Run post-review browser QA and produce short named videos for a locked happy path and sourced browser edge cases. Use when the user wants concise reviewer evidence for a web journey. Not for API, CLI, automated tests, diff review, or application fixes.
fetch-url-as-markdown
Fetch a web page (URL) and return clean Markdown via local trafilatura, with Exa MCP as a fallback for JS-rendered or anti-bot pages. Use when the user asks to read, fetch, scrape, summarize, or quote a URL — prefer this over the built-in WebFetch tool. Don't use for binary files (PDFs, images, archives) or for…