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/sunrisesillneversee/sigrank-app/agents-mdgit clone --depth 1 https://github.com/SunrisesIllNeverSee/sigrank-appWrote 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/sunrisesillneversee/sigrank-app/agents-md)<a href="https://agentmods.dev/instructions/sunrisesillneversee/sigrank-app/agents-md"><img src="https://agentmods.dev/badge/instructions/sunrisesillneversee/sigrank-app/agents-md.svg" alt="Measured on agentmods" 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 | $0.02594 | $0.02594 |
| Opus 5 | $0.01297 | $0.01297 |
| Sonnet 5 | $0.00519 | $0.00519 |
| Haiku 4.5 | $0.00259 | $0.00259 |
Grade A, and why
sigrank-app AGENTS.md scanned grade A 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
client (`sigrank-mcp`) has a curl fallback in `tools.mjs` — when `fetch` gets a How it starts
The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — sigrank-app
Deploy target. Push
main→ Vercel auto-builds → signalaf.com.
Quick reference
| What | Command |
|---|---|
| Type check | npx tsc --noEmit |
| Canonical tests | npm run test:canonical (11/11, MOSES Υ 18436.98) |
| All unit tests | npm test |
| UI tests | npm run test:ui |
| E2E tests | npm run e2e (needs deployed URL or local server) |
| Lint | npm run lint |
| Build | npm run build (needs Node 22; local machine has Node 25 — may fail) |
| Dev server | npm run dev (needs Node 22; local machine has Node 25 — won't start) |
| DNS-AID publish (sigeconomy.com) | CLOUDFLARE_API_TOKEN=<dns-write> node scripts/dns-aid/cloudflare-dns-aid.mjs |
| DNS-AID publish (signalaf.com) | PORKBUN_API_KEY=... PORKBUN_SECRET_API_KEY=... node scripts/dns-aid/porkbun-dns-aid.mjs |
| DNS-AID verify | node scripts/dns-aid/verify-dns-aid.mjs [domain] |
Bun (faster alternative): All test/typecheck commands also work with Bun, which is ~10-30x faster than npm for install + script startup:
| What | Bun command |
|---|---|
| Install deps | bun install |
| Type check | bunx tsc --noEmit |
| Canonical tests | bun run test:canonical |
| All unit tests | bun run test |
| Lint | bun run lint |
Bun is installed at ~/.bun/bin/bun (v1.3.13). It reads the same package.json
scripts and package-lock.json — no migration needed. Use bunx instead of
npx for one-off package execution (e.g. bunx tsc, bunx vitest).
Local dev caveat: Machine runs Node 25, repo pins Node 22 (.nvmrc).
next dev and next build may not start locally. Verify via tsc --noEmit +
canonical tests + live-DOM checks against deployed signalaf.com.
Verification protocol (before every commit)
npx tsc --noEmit— 0 errorsnpm run test:canonical— 11/11 pass- If touching API routes or scoring logic, run full
npm test
Frozen invariants (never change)
- MOSES seed values:
(1_251_211, 11_296_121, 128_196_310, 2_555_179_769)→ Υ 18436.98 - Upsilon (Υ) formula:
(cache_read × output) / input² - 10xDEV formula:
log₁₀(Leverage) - RS.xx weights: server-only, marked
OPERATOR_OVERRIDE_REQUIRED - Canonical test:
__tests__/ingest/canonical.test.mjsmust pass 11/11
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.
- 5d ago First seen · 235 lines · 2,594 tokens per session scan A a34a8fc323a7
sigrank-app AGENTS.md is an instructions file published in the GitHub repository SunrisesIllNeverSee/sigrank-app (6 stars, last pushed yesterday), licensed MIT. It adds 2,594 tokens to every session, about $0.0130 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
yournextstore AGENTS.md
AGENTS.md instructions for yournextstore/yournextstore, covering agents.md, commands, key files & directories, platform-managed files — do not modify and project patterns.
stripekit AGENTS.md
Instructions for rafaelcg/stripekit, covering agents.md, what this is, layout, setup & commands and releasing.
yournextstore CLAUDE.md
Claude Code instructions for yournextstore/yournextstore, a project described as: AI-Native Open-Source Next.js commerce. Powered by Stripe. Ultra fast with typesafe Commerce SDK. Built for AI development (Claude, Codex, Cursor).
skill-rank AGENTS.md
Instructions for davidcjw/skill-rank, covering agents.md — skillrank, what this is, commands, where things live and conventions.
tezgah CLAUDE.md
Instructions for komunite/tezgah, covering tezgah, proje yapısı, skill'ler, kurallar and varsayılan tech stack.
stripekit CLAUDE.md
Instructions for rafaelcg/stripekit: See AGENTS.md for guidance on working in this repository.