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/lamasu/physical-capability-cloud/pccnpx skills add LamaSu/physical-capability-cloud --skill pccgit clone --depth 1 https://github.com/LamaSu/physical-capability-cloudWhat 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 | $0.00051 | $0.02952 |
| Opus 5 | $0.00026 | $0.01476 |
| Sonnet 5 | $0.00010 | $0.00590 |
| Haiku 4.5 | $0.00005 | $0.00295 |
Grade A, and why
pcc scanned grade A with 1 finding 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 yesterday.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST https://capability.network/api/auth/provision \ How it starts
The opening of the file, as written. The whole thing — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PCC — Physical Capability Cloud
You are acting as an agent that discovers and hires real-world physical capabilities through PCC. This skill teaches you the HTTP API — auth, discovery, and the two ways to commit to a job.
What PCC is
PCC is AWS for the physical world: a cloud control plane for physical manufacturing, lab, and logistics capabilities.
| AWS concept | PCC equivalent |
|---|---|
| Availability Zone | Shop Kernel — a physical site (workshop, lab, factory) with equipment |
| Billable service | Capability — not a machine, but what it can do (3D printing, CNC milling, HPLC analysis, courier dispatch) |
| SLA tier | Assurance Tier (0–3) — how much evidence backs a completed job, from self-attested to full multi-verifier proof |
| Payment | Milestone escrow on-chain (Base) — funds release only when evidence meets the tier |
Operators register what their equipment can do; you, acting for the user, find them, agree a price, commit to the job, and verify the outcome before reporting success back to the user.
Base URL
https://capability.network
Every path below is relative to this. The full machine-readable surface is
also published as an OpenAPI 3 document (GET /openapi.json) and as a
single-file agent package (GET /agent-package.json — 250+ tools with
JSON-Schema inputs and HTTP endpoint mappings, built for any LLM that isn't
Claude and doesn't have this skill loaded).
Authenticate
Most reads are public. Posting a job, uploading files, or committing to settlement needs a Bearer key.
curl -X POST https://capability.network/api/auth/provision \
-H "Content-Type: application/json" \
-d '{"email": "[email protected]", "name": "My Agent"}'
Returns { api_key, key_id, operator_id, scopes, rate_limit, expires_at }.
Save api_key — it is not shown again. Send it on every subsequent request:
Authorization: Bearer pcc_live_...
(walletAddress instead of email works too, and SIWE — Sign-In-with-Ethereum
— is available via GET /api/auth/nonce + POST /api/auth/verify if the
user prefers a wallet-only flow.)
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.
- yesterday First seen · 282 lines · 51 tokens per session scan A 77297620d8f5
pcc is a skill published in the GitHub repository LamaSu/physical-capability-cloud (1 stars, last pushed 4d ago), licensed Apache-2.0. It adds 51 tokens to every session and 2,952 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.
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…
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…