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 skills/x-cmd/x-cmd/devloopnpx skills add x-cmd/x-cmd --skill devloopgit clone --depth 1 https://github.com/x-cmd/x-cmdWhat 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 | $0.00025 | $0.00731 |
| Opus 5 | $0.00013 | $0.00365 |
| Sonnet 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 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 — 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.
- 2d 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 (4,624 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. 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
explain-changes
Explain how the code on the current branch works, as an HTML page opened in the browser, written so someone can understand the change and review it. Use when asked to explain a branch, explain these changes, walk me through this code, help me review this, or explain what an agent just did. Most useful when someone…
code-snippet-images
Generate beautiful code snippet images (PNG) for social media, tweets, LinkedIn, and documentation. Creates light-themed, macOS-style window chrome screenshots from code using HTML templates and Chrome headless. Use when asked to create code images, tweet images, snippet screenshots, code cards, or visual code…
userscripts
Use when writing Tampermonkey/Violentmonkey/Greasemonkey userscripts, modifying website behavior or appearance, or working with .user.js files.
stale-sweep
Sweep the googleapis/mcp-toolbox repo for issues and PRs with no real activity in N days (default 60), sort each by whose silence it is (the author's, ours, or nobody's), and draft the nudge or close comment. Use whenever a maintainer asks for a stale sweep, backlog cleanup, or an SLO check, e.g. "stale sweep", "find…
dingtalk_channel_connect
Use a headed browser to automatically complete DingTalk channel integration for QwenPaw. Applicable when the user mentions DingTalk, developer console, Client ID, Client Secret, bot, Stream mode, binding or configuring a channel. Supports pausing when a login page is detected and resuming after the user logs in.
github-issue-triage
Issue triage and lifecycle management agent for ZeroClaw. Use this skill whenever the user wants to: triage open issues, close stale/duplicate/fixed issues, apply labels, run a backlog sweep, enforce the current issue stale policy, or handle a specific issue. Trigger on: 'triage issues', 'issue triage', 'sweep…