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/rjroy/vibe-garden/initnpx skills add rjroy/vibe-garden --skill initgit clone --depth 1 https://github.com/rjroy/vibe-gardenWrote 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/skills/rjroy/vibe-garden/init)<a href="https://agentmods.dev/skills/rjroy/vibe-garden/init"><img src="https://agentmods.dev/badge/skills/rjroy/vibe-garden/init.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 5.1 | $0.00054 | $0.00743 |
| Opus 5 | $0.00027 | $0.00371 |
| Sonnet 5 | $0.00011 | $0.00149 |
| Haiku 4.5 | $0.00005 | $0.00074 |
Grade A, and why
init 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 5d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Init
Bootstrap the project wiki and register a durable scheduled lint job.
Dependencies
This skill requires CronCreate and CronList to be available in the Claude Code harness. If those tools are not present, the wiki directory and Markdown index will still be created, but the scheduled lint job cannot be registered — inform the user that scheduling is unavailable.
Steps
1. Create the wiki directory.
Check whether .lore/reference/ exists. If not, create it. Then check whether .lore/reference/index.md or .lore/reference/index.html exists.
If neither index exists, write a minimal Markdown file at .lore/reference/index.md:
---
title: Field Guide Index
date: YYYY-MM-DD
status: current
tags: [index, field-guide]
---
# Field Guide Index
Never overwrite an existing index. If index.html already exists and index.md does not, leave it in place; the other field-guide skills can read either format.
2. Check for an existing lint job.
CronCreate jobs auto-delete when they expire, so any job present in CronList is by definition active. The check is simply: is the job ID present in the CronList results?
Proceed as follows:
- Read
.lore/reference/.field-guide.json. If it contains alint_job_id, call CronList and check whether that ID appears in the results. If it does, skip to the summary step — do not create a second job. - If
.field-guide.jsonis absent, unreadable, or contains nolint_job_id, call CronList and scan for any job whose prompt is/field-guide:lint. If one is found, write its ID to.field-guide.json(preserving any existingschedulevalue, or omitting it if unknown), then skip to the summary step. - Only proceed to CronCreate if no matching job was found by either path.
3. Translate the schedule value.
Before calling CronCreate, convert the user's requested schedule to a 5-field cron expression:
daily→"3 8 * * *"(08:03 every day)weekly→"3 8 * * 1"(08:03 every Monday)- A raw 5-field cron expression → pass through unchanged
- No schedule provided → default to
"3 8 * * *"
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.
- 5d ago First seen · 73 lines · 54 tokens per session scan A 71bf106ba090
init is a skill published in the GitHub repository rjroy/vibe-garden (6 stars, last pushed 2mo ago), licensed MIT. It adds 54 tokens to every session and 743 once invoked, about $0.0003 per session on Opus 5. 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 skills, from other repositories
deep-project
Decomposes vague, high-level project requirements into well-scoped planning units for /deep-plan. Use when starting a new project that needs to be broken into manageable pieces.
bottle
Bootstrap a new or existing project with a small, file-based documentation system so Claude Code keeps context, lessons, and decisions across session restarts instead of starting cold every time. Sets up a handful of markdown files under .claude/ (standing rules, a free-form note to your next session, a phased…
next
One-step rpm orchestrator, or a bounded internal sequence when given a count or scope. Runs preflight maintenance, then starts the next obvious backlog action (or, in direct use, asks for clarification when nothing is clearly next). With no argument it runs one step; with N, blocked, all, or a group name it runs…
research
Exhaustive multi-agent research on any topic. Parallel search, URL fetching, gap analysis, adversarial validation, citation check. TRIGGER whenever the user asks for research, investigation, or an external look-up — phrasings like 'research X', 'look into X', 'investigate X', 'find out about X', 'what's the latest on…
init-rpm
Project setup and verification. First run creates rpm context for a project. Repeat runs verify that an existing rpm setup matches the latest expected layout and apply safe migrations.
audit
On-demand audit. Target quick runs the mechanical scan.sh only (zero-LLM drift check). Target documents scans docs + agent instructions + memory + session drift via the rpm:auditor review agent. Target project runs a full consultant review — code, architecture, inward + outward research, 7-dimension analysis, saved…