agentmods.dev

markdown-ticket AGENTS.md

Repository instructions for markdown-ticket, covering its documentation, debugging procedures, development tools, and test commands.

In plain words
What is it for?
Use them when changing markdown-ticket, running its frontend, backend, or MCP server, or checking Jest, Playwright, lint, and build results.
Why use it?
They give a coding agent the project-specific information needed to work consistently and investigate problems using the repository's normal procedures.

Instructions file for CodexOpenCode

5 17d ago A scan 2,449 tokens original MIT
View the source file andkirby/markdown-ticket
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/andkirby/markdown-ticket/agents-md
Clone the repo
git clone --depth 1 https://github.com/andkirby/markdown-ticket

Made for: Codex, OpenCode.

Per session 2,449 This file is loaded in full into every session.
When invoked 2,449 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 $0.02449 $0.02449
Opus 5 $0.01224 $0.01224
Sonnet 5 $0.00490 $0.00490
Haiku 4.5 $0.00245 $0.00245

Measured 2d ago against content hash 52000b97f250, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

markdown-ticket 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 · 202 lines

How it starts

The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for Claude Code working with this repository.

Operational Debugging

See DEBUG.md for verified runtime procedures including:

  • Start/stop/restart commands for all runtimes
  • Observation channels (logs, output)
  • Live execution mechanisms
  • Test execution evidence

Skill usage

Load the skills accordingly: @docs/SKILLS.md

Toolchain

  • Runtime: bun (package manager, test runner, dev servers)
  • Test Frameworks: Jest (server unit tests), Playwright (E2E)

Development Commands

Frontend

  • bun run dev - Dev server (localhost:3075)
  • bun run build - Production build
  • bun run lint - ESLint

Backend

  • bun run dev:server - Dev server with nodemon (localhost:3001)
  • bun run server - Production mode
  • bun run --cwd server jest - Jest tests

MCP Server

  • bun run --cwd mcp-server build - Build (required after code changes)
  • bun run --cwd mcp-server dev - Dev mode (stdio, uses tsx)
  • MCP_HTTP_ENABLED=true bun run dev - Stdio + HTTP transports
  • bun run --cwd mcp-server jest - Jest tests

HTTP Transport:

  • Enable: MCP_HTTP_ENABLED=true
  • Port: MCP_HTTP_PORT=3002 (default)
  • Test: bunx @modelcontextprotocol/inspector --transport streamable-http --server-url http://localhost:3002/mcp
  • Optional Phase 2: Session management, SSE streaming, rate limiting, auth, origin validation

Full Stack

  • bun run dev:full - Recommended - Builds shared code, starts frontend + backend

Testing

  • bun run test:e2e - Playwright E2E
  • PWTEST_SKIP_WEB_SERVER=1 bunx playwright test tests/e2e/file.spec.ts --project=chromium - Run specific test without server restart

See tests/AGENTS.md for E2E testing ports, isolation, and conventions.

Code Analysis Tools

  • scip-finder <symbol> - Search for symbols in SCIP code intelligence indexes (more accurate than grep)
    • --scip <path> - Path to SCIP index file (auto-discovers if not provided), you should use the one from root: index.scip
    • --from <file> - Filter to symbols defined in specific file
    • --folder <path> - Filter occurrences to files within folder
    • --format json - Output JSON for programmatic analysis
    • Examples:
      • Find usages of Ticket declared in a certain file: scip-finder --from shared/models/Ticket.ts Ticket
      • Find usages of method Ticket.save(): scip-finder Ticket.save()
      • Find usages of myFunction declared in handler.ts: scip-finder --from handler.ts myFunction
  • bun run inspect:config - Inspect where each configuration setting lives (browser vs backend file, and its exposure class). See docs/CONFIG_INSPECTION.md.
    • --json - Machine-readable output for agents
    • --summary - Counts per exposure class
    • --scope <project|global|user|registry|browser> / --exposure <editable|guarded|readOnly|fileOnly|browser-only> / --filter <substring> - filters

Read the full file on GitHub · 202 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. 2d ago First seen · 202 lines · 2,449 tokens per session scan A 52000b97f250

Subscribe to this mod's changes

markdown-ticket AGENTS.md is an instructions file published in the GitHub repository andkirby/markdown-ticket (5 stars, last pushed 17d ago), licensed MIT. It adds 2,449 tokens to every session, about $0.0122 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.

Related

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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.

openai/codex · 5,182 tokens

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.

langchain-ai/langchain · 4,345 tokens

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).

microsoft/vscode · 5,001 tokens

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.

vercel/next.js · 7,296 tokens