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/atomgit-atomcode/atomcode/atomcode-automation-recommendernpx skills add atomgit-atomcode/atomcode --skill atomcode-automation-recommendergit clone --depth 1 https://github.com/atomgit-atomcode/atomcodeWhat 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 | $0.00071 | $0.03429 |
| Opus 5 | $0.00036 | $0.01715 |
| Sonnet 5 | $0.00014 | $0.00686 |
| Haiku 4.5 | $0.00007 | $0.00343 |
Grade C, and why
setup scanned grade C with 2 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
2. 权限不足 — 尝试 sudo 或检查目录权限 Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
cat .mcp.json 2>/dev/null || echo '{}' How it starts
The opening of the file, as written. The whole thing — 394 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AtomCode Automation Recommender
Analyze codebase patterns to recommend tailored AtomCode automations, then offer to install them.
Core Principles
- Recommend first, install on request — output recommendations, then ask "要我帮你装上吗？"
- Online search first, local fallback — try
npx skills findfor the latest community skills; fall back to reference files if Node.js unavailable - Friendly error handling — if tools are missing (no Node.js, no npx), explain clearly and continue with local recommendations
- 1-2 per category — don't overwhelm; surface the most valuable automations
Automation Types
| Type | Best For | How to Install |
|---|---|---|
| Skills | Packaged expertise, workflows, repeatable tasks | npx skills add <pkg> or create .atomcode/skills/<name>/SKILL.md |
| Plugins | Collections of skills, commands, agents, hooks | /plugin marketplace add <url> then /plugin install <name> |
| MCP Servers | External tool integrations (databases, APIs, docs) | Write to .mcp.json (project root) or ~/.atomcode/mcp.json (global) |
| Hooks | Automatic actions on tool events (format, lint, block) | Write to .atomcode/settings.json |
| Subagents | Specialized reviewers (security, performance, a11y) | Create .atomcode/skills/<name>/SKILL.md with reviewer prompt |
| Commands | Quick slash commands (/test, /review, /deploy) | Create .atomcode/commands/<name>.md |
Workflow
Phase 1: Codebase Analysis
Gather project context:
# Detect project type and tools
ls -la package.json pyproject.toml Cargo.toml go.mod pom.xml build.gradle 2>/dev/null
cat package.json 2>/dev/null | head -50
# Check dependencies
cat package.json 2>/dev/null | grep -E '"(react|vue|angular|next|express|fastapi|django|prisma|supabase|stripe)"'
# Check existing AtomCode config
ls -la .atomcode/ CLAUDE.md .mcp.json 2>/dev/null
# Project structure
ls -la src/ app/ lib/ tests/ components/ pages/ api/ 2>/dev/null
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 394 lines · 71 tokens per session scan C 747ec881c253
setup is a skill published in the GitHub repository atomgit-atomcode/atomcode (189 stars, last pushed 2d ago), licensed MIT. It adds 71 tokens to every session and 3,429 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 2 findings (asks for root, reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…