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/kaelsensei/magicaibuilder/continuegit clone --depth 1 https://github.com/KaelSensei/MagicAIBuilderWrote 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.
[](https://agentmods.dev/commands/kaelsensei/magicaibuilder/continue)<a href="https://agentmods.dev/commands/kaelsensei/magicaibuilder/continue"><img src="https://agentmods.dev/badge/commands/kaelsensei/magicaibuilder/continue.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.00540 |
| Opus 5 | $0.00000 | $0.00270 |
| Sonnet 5 | $0.00000 | $0.00108 |
| Haiku 4.5 | $0.00000 | $0.00054 |
Grade A, and why
continue scanned grade A with 0 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 3d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Continue Command - Resume MagicTheOfflining Work
When /continue is invoked, resume work on this app by reloading progress and picking the next pending task.
Step 1: Project Context
- Assume a single app:
MagicTheOfflining/ - Use project rules from
.cursor/rules/*.mdc
Step 2: Read Progress Documentation
- Read
PROGRESS.md - Read
docs/development/magic_the_offlining_step_by_step_dev_plan.md - Optionally skim:
docs/architecture/magic_the_offlining_architecture.mddocs/deployment/PLAY_STORE_DEPLOYMENT.md(if currently in a release/deployment phase)
Step 3: Load Context
- From
PROGRESS.md, extract:- Recently completed items
- Any explicit "Next" / TODO sections
- From
docs/development/magic_the_offlining_step_by_step_dev_plan.md, identify:- The current step
- The next unfinished step(s)
- Check git status (conceptually):
- Current branch
- Uncommitted files
- Whether there are local changes related to an in-progress feature
Step 4: Summarize and Proceed
Without asking for confirmation:
- State:
- Current branch name
- Last commit summary (if available)
- Summarize:
- What has just been done (from
PROGRESS.md) - What is clearly pending (from both docs)
- What has just been done (from
- Choose the next concrete, bite-sized task, prioritizing:
- Finishing an in-progress feature
- Small UX fixes / scraping fixes / SQLite issues before big refactors
- Start implementing that task immediately, following:
- Offline-only / local-first rules
- React Native + TypeScript + SQLite stack conventions
- Version-management rules (stage → commit with conventional message → push)
Expected Files
These live at the project root or in docs/:
PROGRESS.md(root)docs/development/magic_the_offlining_step_by_step_dev_plan.mddocs/architecture/magic_the_offlining_architecture.mddocs/deployment/PLAY_STORE_DEPLOYMENT.md
Usage
Type /continue when you come back to MagicTheOfflining. The AI will:
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.
- 3d ago First seen · 66 lines · 0 tokens per session scan A 9c392da9ea61
continue is a command published in the GitHub repository KaelSensei/MagicAIBuilder (2 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 540 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
spec-plan
Step 4 of the Vibe-Spec workflow. Generate the high-level plan file for every phase in the V2 phase index, each with a scope + status header, so the user has a complete set of plan files to work from.
spec-phases
Step 3 of the Vibe-Spec workflow. Break the V1 spec into sequential, self-contained phases and append a phase index, producing the final V2 spec.
spec-secrets
Audit a Vibe-Spec app for secrets leaking to the browser. A locked-down, redacting command — a local script reads .env and the built bundle, and Claude only ever sees variable NAMES and pass/fail verdicts. Secret values never enter the model's context.
spec-doctor
Read-only environment health check for the Vibe-Spec stack. Detects your OS and reports which prerequisite tools (Git, Node, pnpm, Docker, uv) are installed, their versions, and what each is needed for. Installs nothing.
spec-implement
Step 5 of the Vibe-Spec workflow. Promote a phase plan to detailed, implement it following the vibe-spec references, then update the docs so the spec reflects reality.
spec-refine
Step 2 of the Vibe-Spec workflow. Critique the V0 spec, fill gaps with clarifying questions, then promote it to a V1 spec that maps each piece of functionality to concrete stack tools using the vibe-spec references.