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/jborgia/signaltree/agents-mdgit clone --depth 1 https://github.com/JBorgia/signaltreeWrote 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/jborgia/signaltree/agents-md)<a href="https://agentmods.dev/instructions/jborgia/signaltree/agents-md"><img src="https://agentmods.dev/badge/instructions/jborgia/signaltree/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 | $0.02854 | $0.02854 |
| Opus 5 | $0.01427 | $0.01427 |
| Sonnet 5 | $0.00571 | $0.00571 |
| Haiku 4.5 | $0.00285 | $0.00285 |
Grade A, and why
signaltree 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 4d 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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI agents working with this repository. Two audiences: contributors changing SignalTree source, and agents consuming @signaltree/* packages in downstream apps.
Do not write RFCs
We make the change. TODO.md is where decided-but-not-done work lives; put it
there and go do it.
docs/rfcs/ is an ARCHIVE of decisions already taken, kept for the options that
were rejected and why — that is what stops them being re-proposed. An RFC is
what an OUTSIDE contributor writes to propose something. Creating
docs/rfcs/00NN-my-idea.md for internal work produces a document that reads as
pending when the work has shipped: four RFC statuses said "proposed" or "Accepted"
for work already in a release, and 0012 claimed it had not shipped when all three
of its items had.
For Contributors
Quick-reference distilled from .cursorrules. That file remains the full rulebook — read it before non-trivial changes.
Stack
- Package manager: pnpm 8+ (required — do not use npm/yarn for workspace ops)
- Monorepo tool: Nx
- Language: TypeScript (strict, no
any; preferunknown) - Builds: Rollup for packages & guardrails, Angular CLI for the demo app
- Tests: Vitest
- Node: 18+ LTS
Common commands
# Install
pnpm install
# Build
pnpm run build:all # all packages
nx build core # single package
pnpm run build:production # production build
# Test
pnpm run test:all
nx test core
pnpm nx test guardrails --pool=forks --poolOptions.forks.singleFork
# Lint / format
pnpm run lint:all
pnpm run lint:fix:all
# Demo
pnpm start # dev server
pnpm nx build demo --configuration=production
Bundle size limits (enforced in validation)
| Package | Max size | Max gzipped |
|---|---|---|
core |
15 KB | 5.8 KB |
ng-forms |
10 KB | 4 KB |
enterprise |
8 KB | 3 KB |
guardrails |
12 KB | 4 KB |
schema |
16 KB | 6 KB |
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.
- 4d ago First seen · 221 lines · 2,854 tokens per session scan A 902f83fa6733
signaltree AGENTS.md is an instructions file published in the GitHub repository JBorgia/signaltree (22 stars, last pushed 13d ago), licensed Apache-2.0. It adds 2,854 tokens to every session, about $0.0143 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 2026-08-30.
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).
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.
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.