pcc

An interface for finding and hiring real-world services such as 3D printing, CNC machining, laboratory testing, drone surveys, and courier delivery. It connects software requests to physical sites and their capabilities.

In plain words
What is it for?
Use it to locate physical services, compare or hire providers, commit funds through milestone escrow, and verify completed manufacturing, laboratory, or logistics work.
Why use it?
It provides a defined way to discover providers, agree on a job, arrange payment, and check the evidence that the work was completed.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/lamasu/physical-capability-cloud/pcc
Any agent
npx skills add LamaSu/physical-capability-cloud --skill pcc
Clone the repo
git clone --depth 1 https://github.com/LamaSu/physical-capability-cloud

Made for: Claude Code, Codex.

Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,952 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured yesterday against content hash 77297620d8f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 \
.claude/skills/pcc/SKILL.md · 282 lines

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.)

Read the full file on GitHub · 282 lines

Changes

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.

  1. yesterday First seen · 282 lines · 51 tokens per session scan A 77297620d8f5

Subscribe to this mod's changes

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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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.

obra/superpowers · 37 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

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…

openai/codex · 114 tokens

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…

openai/codex · 113 tokens