signalint: Instructions file for Codex

AGENTS.md

signalint AGENTS.md is an instructions file for Codex, OpenCode from TranQui004/signalint. It costs 1,312 tokens per session, scanned A, original, MIT.

A set of repository instructions for Signalint that tells coding agents how to change its TypeScript code. It covers architecture, coding rules, tests, response formats, dependencies, and trust boundaries.

In plain words
What is it for?
Use it to guide work in the Signalint repository, including strict TypeScript changes, module tests, documentation comments, and schema-sensitive updates.
Why use it?
It gives agents the project's rules before they edit code, helping them avoid type errors, missing tests, and incompatible changes.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is TranQui004/signalint's own configuration. It tells Codex and OpenCode how to work on signalint itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything signalint configures →

Reuse

Borrowing it

Nothing to install: this file belongs to TranQui004/signalint. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/TranQui004/signalint/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/TranQui004/signalint

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for signalint AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/tranqui004/signalint/agents-md/github.svg)](https://agentmods.dev/instructions/tranqui004/signalint/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/tranqui004/signalint/agents-md"><img src="https://agentmods.dev/badge/instructions/tranqui004/signalint/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.

agentmods 80×15 button for signalint AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/tranqui004/signalint/agents-md"><img src="https://agentmods.dev/badge/instructions/tranqui004/signalint/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,312 This file is loaded in full into every session.
When invoked 1,312 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01312 $0.01312
Opus 5.5 $0.00525 $0.00525
Sonnet 5.5 $0.00262 $0.00262
Haiku 4.5 $0.00131 $0.00131

Measured 29d ago against content hash 2dfd84c56f47, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

signalint 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 29d 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.

AGENTS.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Operating rules for Signalint

These are the standards for changing code in this repository. They apply to human contributors and coding agents alike.

Start with ARCHITECTURE.md for how the system fits together, and CONTRIBUTING.md for setup and the pull request process.

Coding standards

  • TypeScript strict mode is mandatory. Never use any — use unknown and narrow, or define a proper type.
  • Functions should do one thing. If a function exceeds ~40 lines, consider splitting it.
  • Every module under src/engines/, src/cache/, src/cluster/, and src/memory/ must have a corresponding test file under test/ before it is considered done.
  • All public functions and MCP tool handlers need a one-line JSDoc comment stating what they do and what they assume about their input.
  • Match the response schema defined in src/schema.ts exactly. It is versioned (schemaVersion) and has external consumers. If you believe the schema needs to change, propose it — do not silently add or rename fields.
  • Engine adapters are the only modules permitted to invoke external processes. Everything above them operates on NormalizedIssue objects.

Trust boundaries

Signalint treats every MCP tool argument as untrusted, because the model supplying it can be prompt-injected by repository content. When changing anything that handles tool input:

  • Validate arguments through the strict schemas in src/toolArguments.ts.
  • Resolve any client-supplied path through src/projectPaths.ts. Do not reimplement containment checks locally.
  • Never pass client-supplied strings to a shell. Adapters spawn a resolved CLI entry point directly.

See SECURITY.md for the full threat model before changing this area.

Verification

Run all four checks before opening a pull request:

pnpm lint
pnpm typecheck
pnpm test
pnpm build

A change is done when a test actually passes, not when the code looks correct.

Read the full file on GitHub · 126 lines

Changes

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.

  1. 29d ago Changed · +4 tokens per session 2dfd84c56f47
  2. 1mo ago Changed · +1 tokens per session 3eb94b250905
  3. 2mo ago First seen · 126 lines · 1,307 tokens per session scan A caf7098130f0

Subscribe to this mod's changes

signalint AGENTS.md is an instructions file published in the GitHub repository TranQui004/signalint (1 stars, last pushed 21d ago), licensed MIT. It adds 1,312 tokens to every session, about $0.0052 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.

Related

signalint AGENTS.md compared with instructions from other repositories

signalint AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
signalint AGENTS.mdTranQui004/signalintInstructions file121d agoMITA1,312Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode