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/cookiechain/cookie-mcp/agents-mdgit clone --depth 1 https://github.com/cookiechain/cookie-mcpWhat 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 | $0.01350 | $0.01350 |
| Opus 5 | $0.00675 | $0.00675 |
| Sonnet 5 | $0.00270 | $0.00270 |
| Haiku 4.5 | $0.00135 | $0.00135 |
Grade A, and why
cookie-mcp 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 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.
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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contributing to cookie-mcp
A local stdio MCP server that exposes Cookie Chain actions to any AI agent. It runs on the contributor's machine and signs with their key — non-custodial by design. This is a community/ecosystem project for all Cookie Chain developers: Cookiebox, Candy Shop, CookieSwap, Baked Bazaar and Hyperlane are venues it uses, not owners. Keep code and docs venue-neutral.
Layout
src/
mcp/server.ts # the ONLY entry point: registers every tool, thin wrappers over core/
core/ # all logic lives here — pure, testable, framework-agnostic
config.ts # constants, program IDs, endpoints
rpc.ts # getConnection()
wallet.ts # key loading, requireWallet(), assertWithinSpendCap()
errors.ts # CookieMcpError — the one error type surfaced to agents
format.ts # rawToUi / uiToRaw / shortAddr — always go through these
http.ts # fetchJson with retry policy
launchpad/ # MomoSwap launchpad: api (HTTP client) + curve (quote math) + positions (PDAs)
# + program (which deployment: PDA scope + error-code build)
domains/ # CookOven `.cook` names: names (rules + pricing) + program (ixs/PDAs/decode)
# + marketplace (market.cookoven.xyz ixs/PDAs/decode) + market (listings, buy/
# sell ops) + shared (reads both halves need — escrow awareness lives here)
liquidity/ # create/add/remove/lock/claim across damm, cpAmm, clmm, cookieswap
nft/ # Baked Bazaar: auctionHouse (writes) + bazaar (reads)
idl/ # committed IDLs (cp_amm, whirlpool, cookie_domains)
scripts/ # smoke.ts (boots server, asserts tool count) + verify-*.ts (live checks)
Golden rule: tools in server.ts stay thin — tool(async (a) => coreFn(a)). All real work
(tx building, encoding, API calls) lives in src/core/, so it can be unit-tested without MCP.
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 · 89 lines · 1,350 tokens per session scan A 971f02f40068
cookie-mcp AGENTS.md is an instructions file published in the GitHub repository cookiechain/cookie-mcp (3 stars, last pushed 4d ago), licensed MIT. It adds 1,350 tokens to every session, about $0.0068 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 instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.