X-CMD is a POSIX-shell toolkit that provides reusable shell modules and on-demand command-line packages for bash, zsh, ash, and dash. It is designed for people and AI agents that need shell utilities, integrations, and agent-related workflows, and the catalogue contains a large collection of skills for using it.
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 skills add x-cmd/x-cmd --skill devloopgit clone --depth 1 https://github.com/x-cmd/x-cmdWrote 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/skills/x-cmd/x-cmd/devloop)<a href="https://agentmods.dev/skills/x-cmd/x-cmd/devloop"><img src="https://agentmods.dev/badge/skills/x-cmd/x-cmd/devloop/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/skills/x-cmd/x-cmd/devloop"><img src="https://agentmods.dev/badge/skills/x-cmd/x-cmd/devloop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00025 | $0.00731 |
| Opus 5.5 | $0.00010 | $0.00292 |
| Sonnet 5.5 | $0.00005 | $0.00146 |
| Haiku 4.5 | $0.00003 | $0.00073 |
Grade A, and why
devloop 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 1mo 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
devloop
Setup
x rule init :ror # or project-specific ruleset
x env use agent-browser # for visual verification
Workflow
goal → rule.yml → code → verify → issue
1. Define goal → write rule.yml
Before coding, create a rule.yml for the task:
goal: "Fix English version showing Chinese tags in Features section"
keyresults:
- kr-1: "English mode Features tags are all English"
- kr-2: "Chinese mode Features tags remain Chinese"
- kr-3: "Build passes with no regressions"
rules:
- id: kr-1-verify
name: english-tags-no-chinese
apply: "src/components/Features.tsx"
level: error
desc:
- When language=en, all details[] items must be English
- No Chinese characters in any tag badge in English mode
Rule fields: id, name, apply, level, desc, tldr. See x rule -h.
MUST include goal and keyresults — the two mandatory fields for every dev task.
2. Execute → visual verification (frontend)
agent-browser open <url> --session <proj> --headed
agent-browser --session <proj> screenshot /tmp/before.png
# ... make changes ...
agent-browser --session <proj> screenshot /tmp/after.png
MUST screenshot before and after. Compare against intent:
- AI vision check: does after.png match the goal?
- If mismatch → iterate and re-screenshot
- Scrub all privacy data (tokens, emails, personal info) before uploading
3. Verify with x rule
x rule scan <files> # fast (~1 min), for inner loop
x rule check <files> # thorough (~10 min)
x rule audit <files> # full report (~30 min)
4. Sync to issue tracker
See issue/SKILL.md. Minimum: post goal, key-results, rule.yml, before/after screenshots to the issue.
Agent tools
x rule scan— Quick check during iterationx rule check— Full compliance before commitagent-browser screenshot— Visual proof before/aftergh issue create/comment— Sync goal + rule.yml to tracker
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.
- 1mo ago First seen · 90 lines · 25 tokens per session scan A ada122e2299c
devloop is a skill published in the GitHub repository x-cmd/x-cmd (4,713 stars, last pushed 3d ago), licensed Apache-2.0. It adds 25 tokens to every session and 731 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
aomi-transact
Build natural-language crypto/DeFi agents and EVM MCP plugins (Claude Code, Cursor, Codex, Gemini). Aomi turns prompts into wallet-signed txs on Ethereum, Base, Arbitrum, Optimism, Polygon, Linea — non-custodial, fork-simulated. 40+ apps: Uniswap, Aave, Lido, Morpho, GMX, Hyperliquid, Polymarket.
dnanexus-integration
DNAnexus cloud genomics platform. Build apps/applets, manage data (upload/download), dxpy Python SDK, run workflows, FASTQ/BAM/VCF, for genomics pipeline development and execution.
latchbio-integration
Latch platform for bioinformatics workflows. Build pipelines with Latch SDK, @workflow/@task decorators, deploy serverless workflows, LatchFile/LatchDir, Nextflow/Snakemake integration.
lambda-gpu-cloud
Safely inspect and operate Lambda Cloud GPU instances through the documented Cloud API and SSH, with explicit approval before billable or destructive actions.
modal-serverless-gpu
Run approved CPU or GPU work through OpenScience computejob on the user's configured Modal account. Use for isolated scientific scripts, dependency provisioning, durable outputs, logs, status, cancellation, and recovery. Never invoke the Modal SDK or CLI directly.
tensorpool-gpu-cloud
Safely inspect and operate TensorPool GPU clusters and jobs using the current tp CLI, with explicit approval before any billable or destructive action.