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 commands/machinepulse-ai/world2agent-plugins/sensor-addgit 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 | $0.00008 | $0.01551 |
| Opus 5 | $0.00004 | $0.00776 |
| Sonnet 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 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 — 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.
- 2d 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 20d 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. 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.