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/wawworld/dynalist-mcp/agents-mdgit clone --depth 1 https://github.com/wawworld/dynalist-mcpWrote 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/wawworld/dynalist-mcp/agents-md)<a href="https://agentmods.dev/instructions/wawworld/dynalist-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/wawworld/dynalist-mcp/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 | $0.04145 | $0.04145 |
| Opus 5 | $0.02073 | $0.02073 |
| Sonnet 5 | $0.00829 | $0.00829 |
| Haiku 4.5 | $0.00415 | $0.00415 |
Grade A, and why
dynalist-mcp 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 — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dynalist MCP Server
Other agent prompt files (e.g. CLAUDE.md) are symlinks to AGENTS.md. All edits should be made in AGENTS.md.
MCP (Model Context Protocol) server that integrates Dynalist.io with Claude and other AI assistants. Allows reading, writing, searching, and organizing Dynalist documents programmatically.
Setup
No build step. Bun runs TypeScript natively.
bun install # Install dependencies
bun run start # Run the MCP server
Warning: MCP Inspector and MCP clients (e.g. Claude Code) connect to a live Dynalist account and can modify and delete data. Make sure your
DYNALIST_API_TOKENpoints to a test account, not your real one. If you are unsure, list all documents and confirm they look like a test account's documents, not real ones.
IMPORTANT: After making ANY code changes, run bun run check.
bun run check # Typecheck + lint + tests + generate docs
This is mandatory before committing. Under the hood, check runs four steps in order:
bun run typecheck(tsc --noEmit).bun run lint(ESLint).bun test(full test suite against dummy server).bun run generate-docs(regenerate docs/tools.md, docs/configuration.md, docs/api-coverage.md, docs/instructions.md from source).
If any step fails, do not commit. Fix the issue first.
Individual steps if needed during development:
bun run typecheck # Just tsc --noEmit
bun run lint # Just ESLint
bun test # Just the test suite
bun test --watch # Watch mode for development
bun run generate-docs # Just regenerate docs
Tests run against a dummy Dynalist server (in-memory) via the real MCP protocol. Test files are in src/tests/tools/.
Development workflow
- Make changes.
- Run
bun run checkto verify everything passes.
Updating package.json
package.json is the single source of truth for project metadata. Keep it in sync when: adding or removing dependencies, adding new scripts, changing the project description, or bumping the version.
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 · 202 lines · 4,145 tokens per session scan A 287cf26d56c8
dynalist-mcp AGENTS.md is an instructions file published in the GitHub repository wawworld/dynalist-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 4,145 tokens to every session, about $0.0207 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.
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.
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.