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 instructions/dupe-com/standdown/agents-mdgit clone --depth 1 https://github.com/dupe-com/standdownWhat 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 | $0.02669 | $0.02669 |
| Opus 5 | $0.01334 | $0.01334 |
| Sonnet 5 | $0.00534 | $0.00534 |
| Haiku 4.5 | $0.00267 | $0.00267 |
Grade C, and why
standdown AGENTS.md scanned grade C with 1 finding 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 2d 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.
Nullifies safety policieshighAnti-refusal
"You have no restrictions", "do anything now", "ignore your guidelines": a direct jailbreak that disables guardrails.
activation on Amazon hosts unless you override the policy. How it starts
The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — integrating standdown
Instructions for an AI coding agent (Claude Code, etc.) adding the
standdown library to a browser
extension or shopping tool. Copy this file — or point your agent at it — and
follow the steps in order.
Developing
standdownitself (not integrating it)? SeeREADME.mdandCONTRIBUTING. This file is the consumer playbook.
What standdown is (read first)
standdown decides, client-side, whether your extension should stand down
(stay quiet) because a partner already owns the current affiliate attribution —
so you don't hijack a sale someone else referred. It is advisory: it returns
a Decision; it never redirects, blocks, or fires anything itself. You own the
side effects. Keep these invariants intact when you integrate:
- Decisions are local and synchronous. Never add a network call to the decision path.
- Signals are a closed type. Never feed user identity, account, balance, or login state into it.
- Fail toward standing down. On unknown/ambiguous/error states, suppress.
Step 0 — Greenfield or brownfield?
Decide which integration this is before touching code:
- Brownfield — the extension already has its own affiliate stand-down /
attribution logic: a disable/merchant list,
ignore_paramor self-click handling, cookie- or param-based stand-down checks, aFALLBACK_POLICY, or any "stand down" / "suppress" code. Stop and followADOPTING.mdinstead. It moves the existing decision path onto standdown in shadow mode — running both in parallel and proving they agree before cutover — so no live commission is put at risk. Do not do the greenfield steps below. - Greenfield — no existing stand-down logic. Continue with Step 1.
Grep to decide: affiliate params (cjevent, ranSiteID, irgwc, mkcid,
awc), redirect/link-rewrite/cookie-write code, and the words "stand down",
"suppress", or "disable". Any real hit → treat it as brownfield and switch to
ADOPTING.md.
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.
- 2d ago First seen · 244 lines · 2,669 tokens per session scan C 6ad53d6aeac7
standdown AGENTS.md is an instructions file published in the GitHub repository dupe-com/standdown (5 stars, last pushed 20d ago), licensed MIT. It adds 2,669 tokens to every session, about $0.0133 per session on Opus 5. A static security scan graded it C with 1 finding (nullifies safety policies). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
rx-browser-bridge-mcp CLAUDE.md
Claude Code instructions for arikw/rx-browser-bridge-mcp, covering claude.md — rx-browser-bridge, what this is, three components, wire protocol and environment.
affiliate-skills CLAUDE.md
Instructions for Gingg7260/affiliate-skills, covering affiliate skills by affitor, repo structure, cli tool: affiliate-check, key rules and data trust levels.
harpist AGENTS.md
Instructions for kenobi-ai/harpist, a project described as: Automate and document any website's underlying API and replay it with your agent.
BraveMCP CLAUDE.md
Claude Code instructions for glatinone/BraveMCP, covering claude.md — bravemcp orchestration instructions, project overview, build & run commands, mcp server (/mcp-server) and claude desktop integration.
Interceptor AGENTS.md
AGENTS.md instructions for Hacker-Valley-Media/Interceptor, covering interceptor agent manual, install modes, core rules, background first (browser + macos) and surface decision.
agent-bridge-for-tab-management-in-firefox AGENTS.md
AGENTS.md instructions for Johnnyzlee/agent-bridge-for-tab-management-in-firefox, covering agents.md, what this is, project structure, commands and code standards.