adopt
CommandBootstrap an existing repo for ForgeDock — triage open issues, apply labels, suggest a starter milestone, and identify first…
Conversational setup of the Actions-minutes budget and ci.mode (remote / local-first / local-attested / auto) in forge.yaml
> /plugin marketplace add RapierCraftStudios/ForgeDock> /plugin install forgedock@forgedock
description: Conversational setup of the Actions-minutes budget and ci.mode (remote / local-first / local-attested / auto) in forge.yaml argument-hint: "<plain-language request, e.g. keep me under 2,000 minutes, run tests locally first>" install: extras
<!-- SPDX-FileCopyrightText: Copyright (c) RapierCraft Studios --> <!-- SPDX-License-Identifier: AGPL-3.0-or-later -->
**Input**: $ARGUMENTS
Turn a plain-language request about GitHub Actions minutes into a valid `ci` block in `forge.yaml`. Deterministic facts come from `forgedock ci budget`; you only map the request to keys and confirm.
1. Read plan and usage: `forgedock ci budget --json`. It gives `plan`, `includedMinutes`, `monthToDate` (across the account), `projected`, `public`, `mode`. A public repo is free hosted minutes: say so and recommend `auto` (it never switches there). 2. Map the request to keys (flat, under `ci:`):
3. Show the projection per mode: `remote` spends about `projected` minutes; `local-first` and `local-attested` spend paid CI only on release or nightly runs. State the budget and reserve you will write. 4. Ask the user to confirm. Only then write it: `forgedock ci budget --set-mode <mode> --budget <N> [--reserve <P>] [--plan <free|pro|team|enterprise>]`. This keeps any `milestone_integration` keys in the `ci:` block. 5. Re-run `forgedock ci budget` and print the resulting mode. To see which local commands match the repo's workflows (same tool pins): `forgedock ci budget --propose --base origin/<base>`.
Never write a key the user did not ask for, and never guess a plan: if `plan` is `unknown`, ask for the included minutes (`--budget`).
ForgeDock — autonomous AI dev pipeline for Claude Code. GitHub as agent memory: issue in, PR out.
Bootstrap an existing repo for ForgeDock — triage open issues, apply labels, suggest a starter milestone, and identify first…
Pull production analytics from GSC, Bing Webmaster, Clarity, Umami, Cloudflare, Stripe, and GA4 — generate insights and create…
Audit agent outputs from an orchestration run — timeline analysis, stall detection, active vs idle time breakdown
Trace a production issue or pipeline failure end-to-end through GitHub artifacts, then file a detailed improvement issue to the…
Autonomous deploy loop — runs until zero open issues remain. Detects pipeline state and resumes from any position. Fully…
Guided idea-to-backlog setup for a new project: interview, defaults, doubts, spike doc, validated orchestrate-ready backlog
Implement tasks incrementally — build, test, verify, commit. Add "auto" to run the whole plan in one approved pass.