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/pasteai/pasteai/setupgit clone --depth 1 https://github.com/pasteai/pasteaiWhat 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 | $0.00000 | $0.01536 |
| Opus 5 | $0.00000 | $0.00768 |
| Sonnet 5 | $0.00000 | $0.00307 |
| Haiku 4.5 | $0.00000 | $0.00154 |
Grade C, and why
setup scanned grade C with 2 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 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -sSL https://raw.githubusercontent.com/pasteai/pasteai/main/install.sh | sh Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sSL https://raw.githubusercontent.com/pasteai/pasteai/main/install.sh | sh How it starts
The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Set up PasteAI on this machine: install the binary, optionally start a persistent server, and configure MCP so Claude can publish documents.
If the user invokes this command with arguments (e.g. /setup remote https://example.com mykey), read mode, URL, and key from the args and skip Step 0. Otherwise work through each step in order.
Use your Bash tool to run commands. Tell the user what you're doing at each step.
Step 0 — Choose mode (skip if args provided)
Ask the user which mode they want:
- Embedded (default) — pasteai starts a local server automatically on first use. Nothing to configure. Best for Claude Code on your laptop.
- Local server — you run
pasteai serveseparately (Docker, systemd, etc.). Best when Claude runs in a container or you want the server always running. - Remote — point at an existing PasteAI instance. Ask for the server URL and optionally an API key.
Note the chosen mode (call it PASTEAI_MODE: embedded, local, or remote). If remote, note PASTEAI_URL and PASTEAI_API_KEY. You will use these in Step 3.
Step 1 — Install the binary
First, check if pasteai is already installed anywhere:
which pasteai 2>/dev/null || \
test -f "$(go env GOPATH 2>/dev/null)/bin/pasteai" && echo "$(go env GOPATH)/bin/pasteai" || \
test -f "$HOME/.local/bin/pasteai" && echo "$HOME/.local/bin/pasteai"
If found, note the full path — call it PASTEAI_BIN. Skip to Step 2.
If not found, choose an install method:
Option A: go install (if Go is available)
which go
If Go is available:
go install github.com/pasteai/pasteai/cmd/pasteai@latest
Then resolve the path:
PASTEAI_BIN="$(go env GOPATH)/bin/pasteai"
$PASTEAI_BIN version
Option B: prebuilt binary (no Go required)
curl -sSL https://raw.githubusercontent.com/pasteai/pasteai/main/install.sh | sh
PASTEAI_BIN="$HOME/.local/bin/pasteai"
$PASTEAI_BIN version
If neither Go nor curl is available, tell the user:
Install Go from https://go.dev/dl/ or download a prebuilt binary from https://github.com/pasteai/pasteai/releases, then re-run /setup. Then stop.
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 · 193 lines · 0 tokens per session scan C af2f922d8514
setup is a command published in the GitHub repository pasteai/pasteai (4 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,536 tokens. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). 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.
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.