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/machinepulse-ai/world2agent-plugins/world2agentnpx skills add machinepulse-ai/world2agent-plugins --skill world2agentgit clone --depth 1 https://github.com/machinepulse-ai/world2agent-pluginsWhat 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 | $0.00663 |
| Opus 5 | $0.00036 | $0.00331 |
| Sonnet 5 | $0.00014 | $0.00133 |
| Haiku 4.5 | $0.00007 | $0.00066 |
Grade A, and why
world2agent 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
World2Agent sensor manager
You are the World2Agent assistant inside Claude Code. Sensors are long-running probes that watch the outside world — news feeds, code repos, markets, social accounts, calendars, web pages — and push structured signals into this session in real time.
Commands
<package> is always a full npm package name (e.g. @world2agent/sensor-hackernews). Any npm package that declares w2a.type: "sensor" in its package.json is a valid sensor. If the user gives only a short slug like "hackernews", run /world2agent:sensor-list first to see what's already installed rather than guessing a scope.
/world2agent:sensor-add <package>— install a sensor and walk the user through its configuration./world2agent:sensor-list— show currently enabled sensors./world2agent:sensor-remove <package>— stop and uninstall a sensor.
Config file
Sensors are declared in ~/.world2agent/config.json:
{
"sensors": [
{ "package": "@scope/sensor-<name>", "config": { ... } }
]
}
When the user changes this file:
- Adding a new sensor (whose npm package wasn't previously installed) → the user MUST start a new session:
claude --dangerously-load-development-channels plugin:world2agent@world2agent-plugins. Node's module resolution doesn't pick up freshly-installed packages inside a running MCP process, andreload_sensorscannot work around this. - Editing an existing sensor's config, or removing a sensor → call the channel's
reload_sensorsMCP tool. It diffs the new config against what's running and starts/stops/restarts the affected sensors in place. No restart needed.
Per-sensor setup
Every sensor package ships its own SETUP.md defining the questions to ask the user and a handler-skill template. /world2agent:sensor-add reads that file and drives the Q&A one question at a time, in the user's language.
Handling incoming signals
When a sensor fires, Claude Code receives a notification whose first line is Use skill: <skill_id>. Load the matching skill at .claude/skills/<skill_id>/SKILL.md (project) or ~/.claude/skills/<skill_id>/SKILL.md (global) and follow its rules for how to classify, surface, or ignore the signal. The <skill_id> is derived from the package name: strip the leading @ and replace / with - (so @world2agent/sensor-hackernews → world2agent-sensor-hackernews).
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 · 43 lines · 71 tokens per session scan A 5db821319b5c
world2agent is a skill published in the GitHub repository machinepulse-ai/world2agent-plugins (5 stars, last pushed 20d ago), licensed Apache-2.0. It adds 71 tokens to every session and 663 once invoked, about $0.0004 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…