agentmods.dev

context-sync AGENTS.md

Repository instructions are a guide for coding agents working on a TypeScript project. They describe the folders, commands, code style, and available testing approach.

In plain words
What is it for?
Use them when modifying the project, choosing the right development command, naming files, or deciding how to test changes.
Why use it?
They reduce guesswork about how the project is organized and how changes should be built, run, and checked.

Instructions file for CodexOpenCode

191 4mo ago A scan 449 tokens original MIT
View the source file Intina47/context-sync
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/intina47/context-sync/agents-md
Clone the repo
git clone --depth 1 https://github.com/Intina47/context-sync

Made for: Codex, OpenCode.

Per session 449 This file is loaded in full into every session.
When invoked 449 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 $0.00449 $0.00449
Opus 5 $0.00225 $0.00225
Sonnet 5 $0.00090 $0.00090
Haiku 4.5 $0.00045 $0.00045

Measured 2d ago against content hash 20ef8e907892, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

context-sync 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 2d 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 · 36 lines

What it actually says

Repository Guidelines

Project Structure & Module Organization

  • src/: TypeScript source for the MCP server and integrations.
  • bin/: CLI setup and install scripts (Node CJS).
  • docs/: User documentation (CONFIG.md, TOOLS.md, DATA.md, TROUBLESHOOTING.md).
  • assets/: Static assets used in docs.
  • dist/: Build output generated by tsc (do not edit by hand).

Build, Test, and Development Commands

  • npm run build: Compile TypeScript to dist/.
  • npm run dev: Run the server from source via tsx.
  • npm run watch: Run with file watching (tsx watch).
  • npm start: Run the built server from dist/.
  • npm run setup: Launch interactive setup (bin/setup.cjs).
  • npm test: Smoke test that prints readiness (no test runner).

Coding Style & Naming Conventions

  • Language: TypeScript (ES2022 modules), strict mode enabled in tsconfig.json.
  • Indentation: 2 spaces (match existing formatting).
  • File naming: kebab-case in src/ (e.g., git-context-engine.ts).
  • Prefer explicit, descriptive function names; keep modules focused.

Testing Guidelines

  • No automated test suite is defined. npm test is a placeholder.
  • If you add tests, keep them close to the feature area and document how to run them.

Commit & Pull Request Guidelines

  • Commit messages follow Conventional Commits (examples: feat:, fix:, perf:, refactor:, chore(release):).
  • PRs should include: a short description, rationale, and any user-facing changes. Link related issues when applicable. Add screenshots only for docs/UI changes.

Configuration & Release Notes

  • User config and platform integration details live in docs/CONFIG.md.
  • Update docs/RELEASE_NOTES.md when shipping user-facing changes.
  • prepublishOnly runs npm run build && npm test, so keep those scripts passing before publish.
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. 2d ago First seen · 36 lines · 449 tokens per session scan A 20ef8e907892

Subscribe to this mod's changes

context-sync AGENTS.md is an instructions file published in the GitHub repository Intina47/context-sync (191 stars, last pushed 4mo ago), licensed MIT. It adds 449 tokens to every session, about $0.0022 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.

context-managementcontext-syncdeveloper-toolsmcp-serversqliteworkspace
Related

Other instructions, from other repositories

ctx AGENTS.md

Instructions for dchu917/ctx: Use the installed ContextFun commands directly when the user types them as a message.

dchu917/ctx · 1,228 tokens

sivtr AGENTS.md

Instructions for Ariestar/sivtr, covering ai agent instructions, project, commands, communication and working agreement.

Ariestar/sivtr · 3,701 tokens

codemark GEMINI.md

Instructions for DanielCardonaRojas/codemark, covering development workflow and debugging with the tui logging system.

DanielCardonaRojas/codemark · 345 tokens

zen CLAUDE.md

Claude Code instructions for sheshbabu/zen, covering claude.md, development commands, build commands, dependencies and go build tags.

sheshbabu/zen · 2,685 tokens

OpenMAO AGENTS.md

Instructions for OpenMAO/OpenMAO, covering agents.md - openmao agent protocol, start here, stay on course, hard rules and working protocol.

OpenMAO/OpenMAO · 1,376 tokens

ai-viewer AGENTS.md

Instructions for netdata/ai-viewer, covering ai-viewer, goals, phase: development (active — started 2026-06-14), what's overridden during development and what stays in force during development.

netdata/ai-viewer · 11,604 tokens