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/wolf-jonathan/workspace-x/agents-mdgit clone --depth 1 https://github.com/wolf-jonathan/workspace-xWhat 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 | $0.00848 | $0.00848 |
| Opus 5 | $0.00424 | $0.00424 |
| Sonnet 5 | $0.00170 | $0.00170 |
| Haiku 4.5 | $0.00085 | $0.00085 |
Grade A, and why
workspace-x 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.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
wsx Repository Instructions
Purpose
This repository contains the wsx CLI. wsx is not a generic file sync tool.
It is a Windows-first AI workspace manager that links existing local
repositories into one workspace directory.
Product Rules
- Treat
README.md, CLI help output, and tests as the current source of truth unless the user explicitly overrides them. - Preserve the core model: a workspace contains
.wsx.jsonand linked repo directories. - Store absolute paths directly in
.wsx.json. .wsx.jsonis local workspace state and should be gitignored by workspaces created withwsx init.- On Windows, link creation must try symlinks first and fall back to directory junctions when permission errors occur.
link_typeis runtime state and must not be stored in.wsx.json.wsx execmust forward argv directly to process execution. Shell behavior is opt-in and explicit.- Commands intended for AI agents should emit clean plain text and support
--jsonwhere structured output is useful. - Ship and maintain a first-party top-level
SKILL.mdso agent platforms can installwsxguidance globally or locally. - Do not emit ANSI color when stdout is not a TTY.
Engineering Priorities
- Windows correctness is first-class from the start.
- Favor a small dependency set and standard-library implementations where practical.
- Keep command output parseable and stable.
- Prefer predictable behavior over convenience magic.
- Avoid features that weaken portability or make AI usage ambiguous.
Expected Project Structure
wsx/
├── main.go
├── cmd/
│ ├── root.go
│ ├── init.go
│ ├── add.go
│ ├── remove.go
│ ├── list.go
│ ├── status.go
│ ├── fetch.go
│ ├── exec.go
│ ├── doctor.go
│ ├── tree.go
│ ├── grep.go
│ ├── prompt.go
│ └── agent.go
└── internal/
├── workspace/
├── git/
└── ai/
Command-Specific Expectations
wsx initcreates.wsx.jsonand ensures.wsx.jsonis added to the workspace.gitignorewithout overwriting existing.gitignorecontents.wsx addstores absolute paths, supports--favorite <NAME>as an input shortcut, detects circular references, and prevents name conflicts.wsx listreports live link health and runtime link type.wsx doctorvalidates stored absolute paths, link health, and stale generated workspace instruction files.wsx fetchis the safe built-in multi-repo sync primitive. Do not replace it with implicit pull behavior.wsx treeis the discovery command. Keep it cheap and readable.wsx grepis the narrowing command. Use it before opening files broadly.- The top-level
SKILL.mdmust stay aligned with the CLI behavior and the design doc invariants.
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 · 84 lines · 848 tokens per session scan A 7f4b8f7f8d21
workspace-x AGENTS.md is an instructions file published in the GitHub repository wolf-jonathan/workspace-x (5 stars, last pushed 4mo ago), licensed MIT. It adds 848 tokens to every session, about $0.0042 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
workflowbuilder CLAUDE.md
Instructions for synergycodes/workflowbuilder, covering workflow builder, quick reference, agent signals, monorepo structure and per-workspace docs.
WorkFlowX CLAUDE.md
Instructions for TreeX-X/WorkFlowX, covering claude.md - workflowx instructions, routing, orchestrator workflow, constraints and file operations.
STAR AGENTS.md
AGENTS.md instructions for wanghao9610/STAR, covering agent instructions, 1. think before coding, 2. simplicity first, 3. surgical changes and 4. goal-driven execution.
airflow CLAUDE.md
Claude Code instructions for apache/airflow, a project described as: Apache Airflow - A platform to programmatically author, schedule, and monitor workflows.
usurahi CLAUDE.md
Instructions for usurahi-project/usurahi, covering 薄氷(うすらひ)— 共通ガイド, 薄氷とは, 共通原則, 会議状態の最小定義 and 起動時.
gza CLAUDE.md
Instructions for mhawthorne/gza: Read AGENTS.md for all project instructions.