A guided setup for adding the standdown library to a browser extension and checking its conformance. The library helps an extension avoid taking affiliate credit when another partner already owns the sale.

For installing standdown, selecting an adapter based on the extension’s permissions, placing checks at affiliate-attribution points, building the extension, and grading the integration.

It provides a prescribed installation and verification process, including a separate path for extensions that already have similar rules. It also keeps attribution decisions local and makes failures favor standing down.

setup — Skill for Claude Code by dupe-com/standdown

Install

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.

Any agent

npx skills add dupe-com/standdown --skill setup

Clone the repo

git clone --depth 1 https://github.com/dupe-com/standdown

Made for: Claude Code.

Or install standdown, the plugin that ships this one along with the rest of its 3 skills, 3 commands.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/dupe-com/standdown/setup/github.svg)](https://agentmods.dev/skills/dupe-com/standdown/setup)

Your own site

<a href="https://agentmods.dev/skills/dupe-com/standdown/setup"><img src="https://agentmods.dev/badge/skills/dupe-com/standdown/setup/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/dupe-com/standdown/setup"><img src="https://agentmods.dev/badge/skills/dupe-com/standdown/setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 749 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00081	$0.00749
Opus 5.5	$0.00032	$0.00300
Sonnet 5.5	$0.00016	$0.00150
Haiku 4.5	$0.00008	$0.00075

Measured 2mo ago against content hash 648a2fb8e8fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

setup 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 2mo 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.

skills/setup/SKILL.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

standdown setup: install → integrate → grade

Thin router. AGENTS.md at the repo root is the source of truth for the greenfield integration loop — install, pick the adapter, gate every attribution firing point on decision.standDown, bundle, and grade with conformanceGrade. Do not summarize those steps from memory; read the file and follow it exactly, in order. (If the standdown repo isn't already local, fetch the raw file: https://raw.githubusercontent.com/dupe-com/standdown/main/AGENTS.md.)

What to do

Confirm the branch first (AGENTS.md Step 0). If the extension ALREADY has its own stand-down / affiliate-attribution logic (a disable list, ignore_param/self-click handling, cookie or param stand-down checks, a FALLBACK_POLICY, or "stand down"/"suppress" code), this is brownfield — STOP and use the adopt skill (/standdown:adopt) / ADOPTING.md instead (shadow-mode migration, parity before cutover). Only proceed here for a greenfield install.
Drive AGENTS.md Steps 1–6 in order against the user's extension: confirm the target, install, pick the adapter by permissions (never add webRequest/webNavigation to a published extension), integrate at the real activation site, bundle, then grade.
Grade with conformanceGrade — the authoritative number (AGENTS.md Step 6): cd standdown/audit && npm install && DISABLE_HOSTS="<hosts you disable>" npx tsx grade/conformance.ts. Target A/A+; fix anything below A and re-grade. grade/grade.ts (the in-browser testext sensor) is optional and routinely reads C (inert) on real host extensions — do not report it as the grade.

Rules

Never break the invariants: decisions stay local and synchronous (no network in the decision path), signals exclude user identity, everything fails toward standing down.
Confirm context before editing, and report what changed (adapter, gated files, build command, final grade) at the end.
Don't restate AGENTS.md here — if it and this file ever disagree, AGENTS.md wins; fix the drift rather than following the stale copy.

Read the full file on GitHub · 52 lines

Changes

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.

2mo ago First seen · 52 lines · 81 tokens per session scan A 648a2fb8e8fe

Subscribe to this mod's changes

setup is a skill published in the GitHub repository dupe-com/standdown (5 stars, last pushed 27d ago), licensed MIT. It adds 81 tokens to every session and 749 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 2026-08-31.

Browser automation Marketing and SEO affiliate affiliate-marketing browser-extension compliance manifest-v3 standdown

setup next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
setupdupe-com/standdown	Skill	5	27d ago	MIT	A	81	Claude Code
chrome-extensionericrisco/rsc-harness	Skill	598	today	MIT	A	76	Claude Code, Codex
browser-extension-patternsorganvm-iv-taxis/a-i--skills	Skill	17	2mo ago	Apache-2.0	A	55	Claude Code
browser-extension-builderfindscripter/everything-skills	Skill	11	today	none	A	96	Claude Code
category-designerGingg7260/affiliate-skills	Skill	5	1mo ago	MIT	A	103	Claude Code, Codex
compliance-checkerGingg7260/affiliate-skills	Skill	5	1mo ago	MIT	A	87	Codex
self-improverGingg7260/affiliate-skills	Skill	5	1mo ago	MIT	A	87	Claude Code, Codex