grackle: Skill for Claude Code

.claude/skills/launch-grackle/SKILL.md

launch-grackle is a skill for Claude Code from nick-pape/grackle. It costs 0 tokens per session (1,174 once invoked), scanned C, original, MIT.

A test launcher that starts a separate Grackle server for one code branch, using temporary ports and its own data folder.

In plain words
What is it for?
Starting an isolated Grackle server, connecting to it with the printed settings, and running tests against branch-specific data.
Why use it?
It keeps multiple coding agents from interfering with one another or changing the real database during testing.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Codex.

This is nick-pape/grackle's own configuration. It tells Claude Code how to work on grackle itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything grackle configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bash .claude/scripts/launch-grackle.sh.

Reuse

Borrowing it

Nothing to install: this file belongs to nick-pape/grackle. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/nick-pape/grackle/main/.claude/skills/launch-grackle/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/nick-pape/grackle

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for launch-grackle

README.md
[![agentmods](https://agentmods.dev/badge/skills/nick-pape/grackle/launch-grackle.svg)](https://agentmods.dev/skills/nick-pape/grackle/launch-grackle)
Your own site
<a href="https://agentmods.dev/skills/nick-pape/grackle/launch-grackle"><img src="https://agentmods.dev/badge/skills/nick-pape/grackle/launch-grackle.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,174 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.01174
Opus 5 $0.00000 $0.00587
Sonnet 5 $0.00000 $0.00235
Haiku 4.5 $0.00000 $0.00117

Measured 7d ago against content hash f30789890c77, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade C, and why

launch-grackle scanned grade C 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 7d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf "$GRACKLE_HOME"
.claude/skills/launch-grackle/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Launch Grackle for Testing

Launches an isolated Grackle server instance with ephemeral ports and a branch-specific home directory. Prevents agents from conflicting with each other or destabilizing the user's real database.

Invocation

/launch-grackle

Prerequisites

  • rush build must have been run (server runs from dist/)
  • If you only changed one package, rush build -t @grackle-ai/<package> is sufficient

Launch

Run the launch script from the repo root as a single Bash call:

bash .claude/scripts/launch-grackle.sh

The script finds 4 free ports, creates a branch-specific home directory, starts the server, waits for it to be ready, reads the API key, generates a pairing code, and prints all connection details. It also writes $GRACKLE_HOME/env.sh for use in follow-up calls.

Using the env in follow-up bash calls

Each subsequent bash call can source the env file to restore all variables:

BRANCH="$(git rev-parse --abbrev-ref HEAD)"
SAFE_BRANCH="$(printf '%s' "$BRANCH" | tr '/' '-' | tr -c 'a-zA-Z0-9_-' '_')"
source "/tmp/grackle-${SAFE_BRANCH}/env.sh"
# Now $GRPC_PORT, $WEB_PORT, $GRACKLE_API_KEY, $SERVER_PID, etc. are available

Pairing / Auth Flow

The web UI uses pairing-code authentication — it does NOT accept the API key directly. You must complete pairing before the browser can access the UI.

How pairing works:

  1. The server generates a 6-character pairing code
  2. A browser hits /pair?code=XXXXXX — this redeems the code and sets a session cookie
  3. All subsequent web requests use the session cookie (valid for 24 hours)
  4. Without a valid session cookie, the browser is redirected to /pair
  5. Pairing codes expire after 5 minutes. Run grackle pair to generate a new one.

For Playwright MCP testing:

  • You MUST navigate to the pairing URL first before testing the web UI
  • Navigate to $PAIRING_URL — this will set the session cookie and redirect to /
  • After that, the browser has a valid session and you can navigate freely
  • If the pairing code has expired, source the env file (above) then generate a new one:
    GRACKLE_URL="http://127.0.0.1:$GRPC_PORT" GRACKLE_API_KEY="$GRACKLE_API_KEY" grackle pair
    

Read the full file on GitHub · 97 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. 7d ago First seen · 97 lines · 0 tokens per session scan C f30789890c77

Subscribe to this mod's changes

launch-grackle is a skill published in the GitHub repository nick-pape/grackle (21 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,174 tokens. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

code-guidelines-go

Go 1.24–1.27 coding guidelines for the dimetron/pi-go AI agent runtime. Use this skill whenever writing, reviewing, or refactoring ANY Go code in pi-go. This covers idiomatic style, error handling, concurrency, project layout, testing (table-driven, fuzz, benchmarks, synctest), new stdlib usage, golangci-lint v2…

dimetron/pi-go · 124 tokens

go-127

What changed in Go 1.27 (released August 2026) and how it changes the way Go is written in pi-go. Use this skill when writing or reviewing Go that could use a 1.27 feature, when bumping the go directive in go.mod, when a build or test behaves differently after a toolchain upgrade, or when code-guidelines-go points…

dimetron/pi-go · 177 tokens

bubbletea-testing

Use this skill whenever writing tests for Bubble Tea (charmbracelet/bubbletea) TUI applications in Go. Triggers include any mention of testing Bubble Tea models, teatest, golden file testing for TUIs, testing tea.Cmd or tea.Msg, snapshot testing terminal output, or writing tests for any Go CLI/TUI that uses the Elm…

dimetron/pi-go · 139 tokens

vhs-e2e-gif

Record a test run, a TUI session, or any terminal command as a GIF with VHS and attach it to a GitHub PR as a release-hosted asset, never a repo commit. Use when asked to record an e2e run, demo a fix on a PR, attach a GIF or screen recording to a pull request, show a test passing visually, or produce a terminal…

dimetron/pi-go · 106 tokens

check-linters-before-commit

Before any commit, run linters, vet, tests, and build verification; do not commit until checks pass.

dimetron/pi-go · 30 tokens

configure-coddy

Change Coddy's own configuration when the user asks for it: edit settings, providers, models, logging, permissions, or find, install, update, and remove MCP servers and skills. Stages UCI-style commands and commits only after the user confirms saving. Load when the user explicitly asks to change a Coddy setting, or…

coddy-project/coddy-agent · 106 tokens