Borrowing it
Nothing to install: this file belongs to linxule/durable-thinking. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/linxule/durable-thinking/main/AGENTS.mdgit clone --depth 1 https://github.com/linxule/durable-thinkingWrote 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/linxule/durable-thinking/agents-md)<a href="https://agentmods.dev/instructions/linxule/durable-thinking/agents-md"><img src="https://agentmods.dev/badge/instructions/linxule/durable-thinking/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.
<a href="https://agentmods.dev/instructions/linxule/durable-thinking/agents-md"><img src="https://agentmods.dev/badge/instructions/linxule/durable-thinking/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00857 | $0.00857 |
| Opus 5.5 | $0.00343 | $0.00343 |
| Sonnet 5.5 | $0.00171 | $0.00171 |
| Haiku 4.5 | $0.00086 | $0.00086 |
Grade A, and why
durable-thinking 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 22d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Durable Thinking Agent Guide
This repository is an independent Git repository nested inside the broader MCP workspace. Run Git commands from this directory and do not stage it through the parent workspace.
Project Shape
- Durable Thinking is a private, remote-only MCP server on Cloudflare Workers.
- Persistence lives in a SQLite-backed Durable Object and is scoped by explicit,
unguessable
sequenceIdvalues. /mcpis the strict current-protocol endpoint./mcp-compatis the hosted-web client compatibility endpoint and is the default documented connection URL.- Authentication supports the private bearer token and Worker-issued OAuth tokens backed by GitHub sign-in and an explicit GitHub-user allowlist.
- The MCP App is the self-contained document at
src/ui/thought-process.html.
Toolchain and Verification
This project intentionally uses npm, overriding the parent workspace's usual Bun default. Use Node.js 22 or newer.
npm ci
npm run verify
npm run verify is the required completion check. It validates the MCP App,
server contract, Registry manifest and version alignment, TypeScript projects,
tests, and a Wrangler dry build. Use narrower scripts while iterating, but run
the complete command before committing or releasing.
Use npm run dev for local development and npm run deploy for an authorized
manual Cloudflare deployment.
Design and Security Invariants
Read CONTRIBUTING.md before changing MCP behavior, storage, OAuth, routing, or
the App. Its numbered invariants are canonical; do not duplicate or weaken them
here.
- Keep MCP HTTP handling stateless. Application continuity belongs to
sequenceId, never transport session state. - Preserve the fixed personal storage principal and ownership checks.
- Treat
/mcpand/mcp-compatas distinct protected resources. OAuth metadata must advertise the exact client-entered path. - Never log thought text, credentials, authorization codes, state payloads, access tokens, refresh tokens, or bearer secrets.
- Never read, display, commit, or overwrite
.dev.vars. Use.dev.vars.examplewhen documenting configuration. - Keep the MCP App self-contained with no undeclared external assets or network dependencies.
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.
- 22d ago First seen · 86 lines · 857 tokens per session scan A 09ddab7a41ad
durable-thinking AGENTS.md is an instructions file published in the GitHub repository linxule/durable-thinking (2 stars, last pushed 4d ago), licensed MIT. It adds 857 tokens to every session, about $0.0034 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 2026-09-24.
Other instructions, from other repositories
plan-forge naming.instructions.md
Azure naming conventions — Microsoft CAF abbreviations, constraints, uniqueness, tagging.
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.