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/web3dev1337/agent-workspace/agents-mdgit clone --depth 1 https://github.com/web3dev1337/agent-workspaceWhat 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 | $0.00437 | $0.00437 |
| Opus 5 | $0.00218 | $0.00218 |
| Sonnet 5 | $0.00087 | $0.00087 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
agent-workspace 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.
What it actually says
Agent Workspace Repo Instructions
Read CLAUDE.md and CODEBASE_DOCUMENTATION.md before making changes.
Release Versioning
package.jsonis the release version source of truth.- Keep
src-tauri/tauri.conf.jsonandsrc-tauri/Cargo.tomlsynced withnpm run release:sync-version. - Run
npm run release:check-versionbefore tagging or shipping a release build. - Release tags must be
v<package.json version>. scripts/tauri/run-tauri-build.jsclears stalebundle/outputs and verifies that installer filenames include the expected version before CI uploads them.
In-place production updates
Terminals use the tmux persistence backend by default. The Node process owns only tmux clients, so a nodemon restart detaches those clients while the shell and agent panes keep running. The new server process re-adopts them after the browser reconnects.
Before updating the running master/ checkout, request
GET http://127.0.0.1:3000/api/sessions/persistence. Proceed with a normal fast-forward update
only when the response reports ok: true, enabled: true, backend: "tmux", and every expected
active terminal appears under managed. Review any orphaned entries before restarting.
With persistence verified:
- Run
git pull --ff-only origin maininmaster/. - Let nodemon restart after server-file changes.
- Verify port 3000, the persistence endpoint, and the browser reconnect. Commander and worktree terminal processes should remain in their tmux panes.
If persistence is disabled, tmux is unavailable, or the managed-session list is incomplete, use
the deferred restart procedure in PLANS/2026-08-15/PROD_UPDATE.md. A restart in that fallback
state can terminate sessions. Never leave nodemon stopped across a stack shutdown.
Client-only changes under client/ need no nodemon restart. Express serves them directly, so a
browser reload is enough.
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.
- 2d ago First seen · 36 lines · 437 tokens per session scan A f7cf9575f7d5
agent-workspace AGENTS.md is an instructions file published in the GitHub repository web3dev1337/agent-workspace (33 stars, last pushed 2d ago), licensed MIT. It adds 437 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.
Other instructions, from other repositories
mcp-shopline CLAUDE.md
Instructions for asgard-ai-platform/mcp-shopline, covering claude.md, project overview, setup & running, run the mcp server directly (stdio json-rpc 2.0) and or auto-detected via .mcp.json when opened in claude code.
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.
Browser4 CLAUDE.md
Instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
crystal CLAUDE.md
Instructions for stravu/crystal, covering crystal - multi-session claude code manager, project overview, references, implementation status: ✅ complete and ✅ implemented features.
agent-ship CLAUDE.md
Instructions for Agent-Ship/agent-ship, covering claude.md, project overview, commands, docker development (recommended) and local development (no docker).
clawock AGENTS.md
Instructions for KCNyu/clawock, covering agents.md - your workspace, every session, kcn 偏好, git hook (one-time setup per clone) and git auto-commit rules.