agentmods.dev

moth AGENTS.md

Project instructions for Moth, a TypeScript and Node.js MCP server that turns error logs into structured, source-backed repair notes. MCP is a way for an AI agent to call tools provided by a local server.

In plain words
What is it for?
It guides work on error normalization, secret removal, stack and framework detection, fix suggestions, local memory, MCP input and output formats, and tests using common Next.js and TypeScript errors.
Why use it?
It keeps the first version focused, predictable, and read-only while defining how errors, secrets, fixes, and project memory should be handled. It also sets the required development and testing conventions.

Instructions file for CodexOpenCode

2 4mo ago A scan 1,253 tokens original MIT
View the source file stfade/moth
Install

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.

agentmods
npx agentmods add instructions/stfade/moth/agents-md
Clone the repo
git clone --depth 1 https://github.com/stfade/moth

Made for: Codex, OpenCode.

Per session 1,253 This file is loaded in full into every session.
When invoked 1,253 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01253 $0.01253
Opus 5 $0.00626 $0.00626
Sonnet 5 $0.00251 $0.00251
Haiku 4.5 $0.00125 $0.00125

Measured yesterday against content hash 2928ff5c7fee, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

moth 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 yesterday.

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 · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md – Moth

Overview

  • TypeScript/Node.js MCP server.
  • Main goal: receive an error log through MCP and return a structured, source-backed fix brief.
  • Moth v0.1 is a lightweight Skill + MCP plugin for validating project-local bug-fix workflows.
  • Keep the MVP small, explicit, and deterministic.
  • Do not build autonomous code editing, crawlers, vector DB, sandbox, backend service, or background watchers unless requested.
  • Moth is read-only by default.

Environment

  • Package manager: pnpm.
  • Local dev should start the MCP server.
  • Prefer simple scripts:
    • pnpm dev
    • pnpm build
    • pnpm test
  • Use environment variables only for optional providers.
  • Never require external services for the first working MVP.
  • Local project memory should use:
.moth/fix-memory.jsonl

Testing

  • Unit tests should cover:

    • secret redaction
    • error normalization
    • fingerprint generation
    • stack/framework detection
    • local memory read/write
    • prior successful fix matching
    • prior failed fix avoidance
    • fix brief generation
    • MCP tool input/output schema

  • A commit must leave the test suite green.

  • Use fixtures for common errors:

    • Next.js
    • TypeScript
    • Prisma
    • Vite
    • ESLint

Coding Conventions

  • Use TypeScript.
  • Prefer simple, readable, deterministic code.
  • File names are kebab-case.
  • Keep modules small and focused.
  • Avoid premature abstractions.
  • Prefer explicit schemas for MCP tool inputs and outputs.
  • Do not hide important behavior behind agents or implicit side effects.
  • Suggested structure:
src/
  server.ts
  tools/
    analyze-error.ts
    remember-fix-result.ts
  core/
    redact.ts
    normalize-error.ts
    fingerprint.ts
    detect-stack.ts
    memory-store.ts
    match-memory.ts
    build-brief.ts
  schemas/
    analyze-error.schema.ts
    remember-fix-result.schema.ts
    fix-brief.schema.ts
    fix-memory-record.schema.ts
  skills/
    moth-debug-first-fix.md
    moth-source-backed-research.md
    moth-verify-fix.md
  fixtures/

Read the full file on GitHub · 196 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. yesterday First seen · 196 lines · 1,253 tokens per session scan A 2928ff5c7fee

Subscribe to this mod's changes

moth AGENTS.md is an instructions file published in the GitHub repository stfade/moth (2 stars, last pushed 4mo ago), licensed MIT. It adds 1,253 tokens to every session, about $0.0063 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.

DebuggingMemory and contextTestingai-coding-agentbug-fixdeveloper-toolsmcpmodel-context-protocol
Related

Other instructions, from other repositories

llm-context.py CLAUDE.md

Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.

cyberchitta/llm-context.py · 582 tokens

openrouter-mcp-multimodal AGENTS.md

Instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).

stabgan/openrouter-mcp-multimodal · 783 tokens

seekstone CLAUDE.md

Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.

shaqmughal/seekstone · 1,116 tokens

Plonk AGENTS.md

Instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.

ostapondo/Plonk · 3,557 tokens

mcp-dockhand copilot-review.instructions.md

Instructions for strausmann/mcp-dockhand: When reviewing pull requests in this repository.

strausmann/mcp-dockhand · 295 tokens

second-brain AGENTS.md

Instructions for LindaHaviv/second-brain, covering instructions for ai coding agents, what to read first, the rules (non-negotiable), common tasks, the sanctioned way and enforcement, not just instructions.

LindaHaviv/second-brain · 1,686 tokens