Borrowing it
Nothing to install: this file belongs to gregcastro23/WhatToEatNext. 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/gregcastro23/WhatToEatNext/master/CLAUDE.mdgit clone --depth 1 https://github.com/gregcastro23/WhatToEatNextWrote 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/gregcastro23/whattoeatnext/claude-md)<a href="https://agentmods.dev/instructions/gregcastro23/whattoeatnext/claude-md"><img src="https://agentmods.dev/badge/instructions/gregcastro23/whattoeatnext/claude-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/gregcastro23/whattoeatnext/claude-md"><img src="https://agentmods.dev/badge/instructions/gregcastro23/whattoeatnext/claude-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 | $0.01674 | $0.01674 |
| Opus 5.5 | $0.00670 | $0.00670 |
| Sonnet 5.5 | $0.00335 | $0.00335 |
| Haiku 4.5 | $0.00167 | $0.00167 |
Grade A, and why
WhatToEatNext CLAUDE.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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WhatToEatNext - Agent Guidance
Build and Test Commands
- Build:
bun run build - Typecheck:
bun run typecheck - Verify:
bun run verify - Test:
bun run test
Agent skills
Issue tracker
Issues and PRDs for this repo live as GitHub issues. Use the gh CLI for all operations. Pull requests are not a request surface for triage. See docs/agents/issue-tracker.md.
Triage labels
The five canonical triage states are mapped 1-to-1 to the labels (needs-triage, needs-info, ready-for-agent, ready-for-human, wontfix). See docs/agents/triage-labels.md.
Domain docs
Uses a single-context domain model layout with CONTEXT.md at the root and ADRs in docs/adr/. See docs/agents/domain.md.
Admin surface
Operator UI lives under src/app/admin/* behind the sidebar in admin/layout.tsx (admin-role + isAdminEmail gated). Every panel reads a live source — never fabricate admin data; degrade to an honest live: false/"no source" state instead.
- Overview (
/admin) —PulseStrip(one live headline per source,GET /api/admin/pulse) then panels insrc/components/admin/*Panel.tsx, each self-polling viauseHardenedPolling, starting withLaunchReadinessPanel. - Live pages —
/admin/traffic,/admin/growth,/admin/revenue,/admin/chain,/admin/code-health. Each readsGET /api/admin/<name>throughuseAdminResource(src/components/admin/live/) and validates with a zod schema insrc/lib/admin/schemas/. Each schema has a compile-time drift guard against its server type, so renaming a server field failstsc. Services live insrc/services/admin/.- Traffic: first-party
page_views(migration 86) written byPageViewTracker→POST /api/track/pageview. It stores no cookies and no raw IPs; the visitor hash rotates daily; bots and/adminare excluded. - Growth: humans only. A human is an account whose email is not on
@agentic.alchm.kitchen;is_agentis not used. - Revenue: read live from the Stripe API (MRR from real prices, 30-day charges, checkout funnel by
metadata.purpose, pending webhook deliveries). - Chain: Solana addresses come from
alchm-agents-solana/deployments/*.jsonon GitHub and are then read live from devnet and mainnet RPC. Anchor layouts are decoded insolanaDecode.ts, with golden-vector tests. Also shows Base Sepolia operator gas and the claim ledger. - Code health: tsc/ESLint readings arrive from the CI
code-healthjob, which posts toPOST /api/admin/code-health/ingestusingCODE_HEALTH_INGEST_SECRET. Also shows the bundled ratchet baselines, their GitHub history, CI status, commits, and PRs.bun run health:snapshotmeasures locally. SetGITHUB_TOKENto lift the unauthenticated GitHub rate limit.
- Traffic: first-party
- Jobs & probes (
/admin/jobs,GET /api/admin/jobs) shows every cron and synthetic probe fromsrc/services/cronRegistry.ts, which imports vercel.json and appends Railway jobs such asdaily-digest. For each job it shows:- state, using the same
evaluateHeartbeatverdict as the alerting cron; - runs owed versus recorded in the last 24h (a run Vercel kills at
maxDurationleaves no row); - p95 against the function limit;
- its last 24 runs.
- state, using the same
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 · +14 tokens per session 9cf488b0ebec
- 1mo ago Changed · +26 tokens per session c401fb009b27
- 1mo ago Changed · +41 lines · +1,086 tokens per session 7d3d024c8a39
- 2mo ago First seen · 34 lines · 548 tokens per session scan A f25aa6120972
WhatToEatNext CLAUDE.md is an instructions file published in the GitHub repository gregcastro23/WhatToEatNext (0 stars, last pushed today), licensed MIT. It adds 1,674 tokens to every session, about $0.0067 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.
WhatToEatNext CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| WhatToEatNext CLAUDE.mdgregcastro23/WhatToEatNext | Instructions file | 0 | today | MIT | A | 1,674 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 144k | today | MIT | A | 8,130 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 150k | today | MIT | A | 4,680 | Codex, OpenCode |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 283k | today | MIT | A | 4,342 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 3,153 | GitHub Copilot |