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/claude-mdgit clone --depth 1 https://github.com/wolf-jonathan/workspace-xWrote 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/wolf-jonathan/workspace-x/claude-md)<a href="https://agentmods.dev/instructions/wolf-jonathan/workspace-x/claude-md"><img src="https://agentmods.dev/badge/instructions/wolf-jonathan/workspace-x/claude-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 | $0.00414 | $0.00414 |
| Opus 5 | $0.00207 | $0.00207 |
| Sonnet 5 | $0.00083 | $0.00083 |
| Haiku 4.5 | $0.00041 | $0.00041 |
Grade A, and why
workspace-x CLAUDE.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 3d 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
wsx - AI Workspace Manager
What this is
A Go CLI that manages a workspace directory by linking existing local
repositories into one AI-friendly workspace. The workspace stays portable
because committed config keeps ${VAR} placeholders and local machine state
lives in .wsx.env.
Project layout
cmd/: Cobra command entrypoints. Keep command files thin.internal/workspace/: config, env loading, path resolution, and link handling.internal/git/: shared git command runner and repo operations.internal/ai/: AI-facing tree, grep, prompt, agent, and skill helpers.README.md: public product and usage documentation.SKILL.md: bundled agent guidance shipped with the repo.
Core invariants
.wsx.jsonstores portable paths and must keep${VAR}placeholders intact.- Placeholder resolution happens at point of use via
internal/workspace/env.go. .wsx.envis local-only state and must never be committed by generated workspaces.link_typeis runtime state. Detect it from disk; do not persist it in.wsx.json.- On Windows, link creation tries symlinks first and falls back to junctions on permission errors.
wsx execforwards argv directly to process execution. Shell behavior is opt-in and explicit.- Commands intended for AI use should emit clean plain text and support
--jsonwhere structured output is useful. - Do not emit ANSI color when stdout is not a TTY.
Working rules
- Treat
README.md, CLI help text, and tests as the product source of truth unless explicitly changed. - Preserve the workspace model: workspace root plus
.wsx.json,.wsx.env, and linked repo directories. - Prefer small, reviewable changes and reuse shared internal seams instead of duplicating logic in commands.
- If behavior changes, update
README.mdandSKILL.mdso the docs stay aligned with the CLI.
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.
- 3d ago First seen · 36 lines · 414 tokens per session scan A 47ecb78ab325
workspace-x CLAUDE.md is an instructions file published in the GitHub repository wolf-jonathan/workspace-x (5 stars, last pushed 4mo ago), licensed MIT. It adds 414 tokens to every session, about $0.0021 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
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.
superpowers-graph CLAUDE.md
Claude Code instructions for RonMizrahi/superpowers-graph, covering superpowers-graph — repository guide, sources of truth, changing the graph — the eval ships with the change and rules that are not obvious from the code.
duet CLAUDE.md
Claude Code instructions for tslateman/duet, covering duet, lint, project structure, skill directory contents and eval scenario contents.