Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add machinepulse-ai/world2agent-plugins/plugin install world2agentWrote 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/commands/machinepulse-ai/world2agent-plugins/sensor-add)<a href="https://agentmods.dev/commands/machinepulse-ai/world2agent-plugins/sensor-add"><img src="https://agentmods.dev/badge/commands/machinepulse-ai/world2agent-plugins/sensor-add/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/commands/machinepulse-ai/world2agent-plugins/sensor-add"><img src="https://agentmods.dev/badge/commands/machinepulse-ai/world2agent-plugins/sensor-add.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00008 | $0.01551 |
| Opus 5.5 | $0.00003 | $0.00620 |
| Sonnet 5.5 | $0.00002 | $0.00310 |
| Haiku 4.5 | $0.00001 | $0.00155 |
Grade A, and why
sensor-add 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 2mo 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add a sensor for the user from package $ARGUMENTS. $ARGUMENTS MUST be a complete npm package name (e.g. @world2agent/sensor-hackernews) — never guess, never auto-prepend a scope.
If the user gives a short slug like hackernews, resolve it first: run /world2agent:sensor-list or ask the user once for the full name. Any npm package with w2a.type: "sensor" metadata is a valid sensor.
0. Validate the input (security gate — do this BEFORE anything else)
$ARGUMENTS is going to be passed to npm install as a shell argument. Before you do anything else, confirm it is only an npm package name:
- It must match this regex exactly:
^(@[a-z0-9][a-z0-9_-]*\/)?[a-z0-9][a-z0-9._-]*$ - It must contain no whitespace, no shell metacharacters (
;,&,|,`,$,(,),<,>,',",\, newline), no.., and no URL scheme (http://,git+…,file:…). - Reject anything that looks like a tarball path or git URL, even if npm would technically accept it. Users who need those can hand-edit
~/.world2agent/config.json.
If $ARGUMENTS fails any of these checks, refuse and stop. Tell the user what looked wrong and ask them to re-issue the command with a plain npm package name. Do not try to "sanitize" the input yourself.
Conversation language
Run the entire Q&A in the user's current conversation language (infer from their recent messages; if unclear, fall back to the device/system locale). The questions in SETUP.md are templates — translate them into the user's language before asking. Don't dump English questions on a Chinese user, or vice versa.
Naming convention (everything is derived from the full package name)
- npm package:
$ARGUMENTS(any valid npm package name) - skill_id (directory name): output of
packageToSkillId($ARGUMENTS)— strip the leading@, replace/with-. E.g.@world2agent/sensor-hackernews→world2agent-sensor-hackernews,@acme/my-source→acme-my-source - handler skill path:
.claude/skills/<skill_id>/SKILL.md
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.
- 2mo ago First seen · 113 lines · 8 tokens per session scan A 2f580c10f37a
sensor-add is a command published in the GitHub repository machinepulse-ai/world2agent-plugins (5 stars, last pushed 7d ago), licensed Apache-2.0. It adds 8 tokens to every session and 1,551 once invoked, about $0.0000 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 2026-08-31.
sensor-add compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sensor-addmachinepulse-ai/world2agent-plugins | Command | 5 | 7d ago | Apache-2.0 | A | 8 | Claude Code |
| tapeoutrjwalters/kicad-tools | Command | 73 | yesterday | MIT | A | 0 | Claude Code |
| eol-reportWYRE-AI/msp-claude-plugins | Command | 52 | 2d ago | Apache-2.0 | A | 28 | Claude Code |
| rvcsi-calibrateruvnet/rvcsi | Command | 29 | yesterday | Apache-2.0 | A | 20 | Claude Code |
| esp-hardenmathisk2095/jko-claude-plugins | Command | 3 | 26d ago | MIT | A | 17 | Claude Code |
| pentest-wirelessJoasASantos/ClaudeAdvancedPlugins | Command | 160 | 8mo ago | MIT | A | 0 | Claude Code |
| device-infophinn/KinetAios | Command | 13 | yesterday | GPL-3.0 | A | 22 | Claude Code |