Borrowing it
Nothing to install: this file belongs to seancrecord/scvd-general-store-repo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/seancrecord/scvd-general-store-repo/main/AGENTS.mdgit clone --depth 1 https://github.com/seancrecord/scvd-general-store-repoWrote 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/instructions/seancrecord/scvd-general-store-repo/agents-md)<a href="https://agentmods.dev/instructions/seancrecord/scvd-general-store-repo/agents-md"><img src="https://agentmods.dev/badge/instructions/seancrecord/scvd-general-store-repo/agents-md/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/instructions/seancrecord/scvd-general-store-repo/agents-md"><img src="https://agentmods.dev/badge/instructions/seancrecord/scvd-general-store-repo/agents-md.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 | $0.02237 | $0.02237 |
| Opus 5.5 | $0.00895 | $0.00895 |
| Sonnet 5.5 | $0.00447 | $0.00447 |
| Haiku 4.5 | $0.00224 | $0.00224 |
Grade A, and why
scvd-general-store-repo AGENTS.md 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 1mo 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI coding agents working in this repo. Kept deliberately
short: research on these files shows unnecessary requirements harm
agent performance, so this is the minimum that is actually load-bearing.
Human-facing product docs live elsewhere (see PROBLEMS.md,
AT_SCALE.md, and the historical record under docs/archive/).
Before working, read HOUSE_RULES.md (the standing rules; rule 29
requires this), KEEPER_LIST.md (his hands — directory entries,
walks, presses, decisions), and
ROADMAP.md (the feature order: now / soon / later). Two
queues, one job each. Do not put a build on the desk.
What this is
scvd.store — an evidence observatory for agentic commerce, run by one
human on Cloudflare Workers (Hono + TypeScript). The store's one real
product is independent signed observation: conformance audits,
endpoint watches, settlement attestations, Bitcoin-anchored
timestamps. Every product ends in an ed25519-signed artifact a third
party can verify without trusting us — and every instrument publishes
the gaps it could not see, counted against itself.
Not an escrow, a guarantor, or a dispute court: those absorb risk and need a balance sheet. We observe the gap and sign what we saw.
It is also a general store selling small signed goods over x402 in USDC.
Checkout rails come from acceptedNetworks() in src/lib/payments.ts;
chain-reading support is broader. PAYMENT_RAILS.md distinguishes them.
Commands
- Install:
npm install - Test (full suite; all CI shards must pass before merge):
npm test - Typecheck:
npm run typecheck - Bundle check (catches build-only breakage tests miss):
npm run build:check - Local dev:
npm run dev - The six doors:
npm run doors:check(reads the live store down all six roads an agent can take — SIX_DOORS.md; read-only, and--recordis a human's hand) - The seventh road is a browser.
.mcp.jsondeclaresscvd-store(the live/mcpdoor). For the browser check, explicitly loadscripts/chrome-devtools.mcp.jsonas an additional MCP configuration (Claude Code:claude --mcp-config scripts/chrome-devtools.mcp.json). Its pinnedchrome-devtoolsserver loads a page in real Chrome and reads whatdocument.modelContextactually registered. The separate file keeps contributor browser tooling out of customer plugin installs. The WebMCP surface is derived from the MCP tool catalogue, so the two answers disagreeing is a defect the unit tests cannot see — they read the same source. Both are read-only in practice:tools/listis free and everybuy_*needs a signed payment that no agent here has. Chrome not on the default path takes--executablePath=<path>; a container with no display takes--headless.
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.
- 1mo ago Changed · +8 lines · +151 tokens per session ef4b395e753e
- 1mo ago Changed · +2 lines · +26 tokens per session c198104b91bb
- 1mo ago Changed · +5 lines · +82 tokens per session c0c98db1d3dd
- 1mo ago Changed · +2 lines · +33 tokens per session 218bf008dffe
- 1mo ago Changed · +13 lines · +213 tokens per session de11b7536e22
- 1mo ago Changed · +2 lines · +25 tokens per session 390197b162d2
- 1mo ago First seen · 132 lines · 1,707 tokens per session scan A 3f8c21d91c2f
scvd-general-store-repo AGENTS.md is an instructions file published in the GitHub repository seancrecord/scvd-general-store-repo (3 stars, last pushed yesterday), licensed MIT. It adds 2,237 tokens to every session, about $0.0089 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.