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/aronprins/paperclip-cli/paperclip-clinpx skills add aronprins/paperclip-cli --skill paperclip-cligit clone --depth 1 https://github.com/aronprins/paperclip-cliWhat 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 | $0.00138 | $0.03639 |
| Opus 5 | $0.00069 | $0.01819 |
| Sonnet 5 | $0.00028 | $0.00728 |
| Haiku 4.5 | $0.00014 | $0.00364 |
Grade A, and why
paperclip-cli scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "$PAPERCLIP_API_URL/api/health" # is the server even up How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Operating the Paperclip CLI (paperclipai)
Core mental model
- Two layers. Setup commands (
onboard,doctor,configure,runwith no subcommand,db:backup,worktree*,env-lab) operate on local config/DB under~/.paperclipand need no credential. Control-plane commands (everything else: company, issue, agent, run<sub>, routine, budget, ...) are HTTP clients for the server API and need an API base + credential. - The CLI never runs the model. Agent work executes server-side in the Paperclip runtime/adapters. The CLI triggers (
agent wake,heartbeat run) and observes (run *). You conduct; the server computes. Sole exception:agent local-clisets up your machine so a local AI acts as that agent and reports back via the API. - Two personas: board operator (instance-wide authority; bootstraps, builds the org, mints credentials) and agent (scoped to exactly one company + one agent). Matching credentials: board API token (
token board create, named/expirable/revocable) and agent API key (token agent create, plaintext shown once). - API base resolution, first match wins:
--api-base→PAPERCLIP_API_URL→ profileapiBase→ local config port →http://localhost:3100. - Context profiles (
~/.paperclip/context.json) store defaults per profile: apiBase, companyId, persona, agentId. They storeapiKeyEnvVarName— the name of an env var, never a plaintext secret. The token stays in your environment.
Quick environment check
Run these first to see what you already have:
env | grep '^PAPERCLIP_' # PAPERCLIP_API_URL / _COMPANY_ID / _AGENT_ID / _API_KEY already exported?
paperclipai context show # active profile: apiBase, companyId, persona, apiKeyEnvVarName, contextPath
paperclipai whoami --json # which identity the current credential resolves to
curl -s "$PAPERCLIP_API_URL/api/health" # is the server even up
If the four PAPERCLIP_* env vars are set, you are almost certainly running as an agent persona already — operate with them directly, no profile needed.
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 · 148 lines · 138 tokens per session scan A 8a8fe8a705a1
paperclip-cli is a skill published in the GitHub repository aronprins/paperclip-cli (18 stars, last pushed 2mo ago), licensed MIT. It adds 138 tokens to every session and 3,639 once invoked, about $0.0007 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 2026-08-30.
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…