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/waishnav/devspace/agents-mdgit clone --depth 1 https://github.com/Waishnav/devspaceWhat 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 | $0.01676 | $0.01676 |
| Opus 5 | $0.00838 | $0.00838 |
| Sonnet 5 | $0.00335 | $0.00335 |
| Haiku 4.5 | $0.00168 | $0.00168 |
Grade A, and why
devspace 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- devs-codex AGENTS.md — 100% identical, 0 lines differ
- MCPishCode AGENTS.md — 92% identical, 25 lines differ
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DevSpace
DevSpace is a local development execution layer for MCP hosts such as ChatGPT and Claude. It gives a remote host workspace-scoped tools for reading, editing, searching, running commands, managing Git worktrees, reviewing changes, and coordinating bounded subagents on the user's machine.
Pi's SDK currently provides mature local coding primitives. DevSpace wraps those primitives in a Streamable HTTP MCP server and adds the product-specific boundaries around them: approved roots, workspace state, instructions, process sessions, worktrees, artifacts, review checkpoints, widgets, and subagent execution.
DevSpace owns tooling mechanics. The model receives only meaningful and actionable choices. The user sees outcomes. Tool defination should not leak internal implementation or it shoudn't be giving unwanted options to model to choose from if tooling can handle this.
Product model
These ideas should stay true as the project evolves:
- The host is the orchestrator. DevSpace exposes clear capabilities and execution state. It should not hide the workflow inside an opaque, uninspectable agent loop.
- Everything happens in a workspace. A workspace represents one local project directory or worktree plus the instructions and state accumulated while operating in it.
- Local authority stays explicit. DevSpace runs with access to the user's machine. Roots, paths, commands, processes, credentials, and destructive operations must be treated as product boundaries.
- Subagents are bounded workers. A subagent should have an explicit task, profile, working context, lifecycle, and result that the host can inspect and coordinate.
- Adapters stay at the edges. Pi, MCP hosts, and model providers each have their own terminology and capabilities. Provider-specific behavior should not become the core domain model.
- Prefer composable primitives. Build a small set of reliable operations that can be combined into larger workflows instead of baking every workflow into the server.
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.
- yesterday First seen · 118 lines · 1,676 tokens per session scan A 47937030f5f0
devspace AGENTS.md is an instructions file published in the GitHub repository Waishnav/devspace (4,271 stars, last pushed 3d ago), licensed MIT. It adds 1,676 tokens to every session, about $0.0084 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.
Other instructions, from other repositories
taskflow AGENTS.md
Instructions for heggria/taskflow, covering agents.md, project overview, architecture, key concepts and phase types (12 total).
myrlin-workbook CLAUDE.md
Claude Code instructions for therealarthur/myrlin-workbook, covering claude workspace manager, critical scope constraint, project goal, tech stack preferences and agent teams.
langgraph AGENTS.md
Instructions for langchain-ai/langgraph, covering agents instructions, corridor security analysis, libraries and dependency map.
kungfu copilot-instructions.md
Instructions for kungfu-systems/kungfu: Read and follow AGENTS.md before proposing or running changes. It is the shared agent router for this repository, including the canonical Shifu development and build entrypoint.
AstrBot copilot-instructions.md
Copilot instructions for AstrBotDevs/AstrBot, covering astrbot development instructions, working effectively, bootstrap and install dependencies, running the application and dashboard build (vue.js/node.js).
chatgpt-cli CLAUDE.md
Instructions for kardolus/chatgpt-cli, covering chatgpt-cli — release runbook, prerequisites, 1. cut the release, 2. publish the github release + binaries and 3. update the homebrew tap.