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 skills add rjroy/vibe-garden --skill lintgit 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/lint)<a href="https://agentmods.dev/skills/rjroy/vibe-garden/lint"><img src="https://agentmods.dev/badge/skills/rjroy/vibe-garden/lint/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/rjroy/vibe-garden/lint"><img src="https://agentmods.dev/badge/skills/rjroy/vibe-garden/lint.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00055 | $0.01088 |
| Opus 5.5 | $0.00022 | $0.00435 |
| Sonnet 5.5 | $0.00011 | $0.00218 |
| Haiku 4.5 | $0.00006 | $0.00109 |
Grade A, and why
lint 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 17d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lint
Health-check wiki structure and surface review candidates. A lint finding is not a verdict that historical intent binds current work; semantic accuracy requires checking implementation/tests and current user direction with resolve-drift.
Steps
1. Load the index.
Read the field-guide index. Prefer .lore/reference/index.md; if it does not exist, read .lore/reference/index.html. Collect every local page link it lists — these are the indexed pages. Links may point to .md or .html files. If no index exists or the index contains no links, report that and stop.
2. Run five checks.
Run all five checks before reporting. Each check has a defined severity; do not promote or demote.
[error] Contradictions
Read every indexed wiki page in full. Pages may be Markdown or HTML. For HTML pages, use meta tags as metadata and visible body content as the page body. Look for pages that make conflicting claims about the same concept, entity, or decision. Two pages contradict each other when they assert incompatible facts about the same subject — not merely when they discuss it differently or at different levels of detail.
For each contradiction found, record:
- Both page paths
- The specific claim each page makes
- The subject they disagree on
[warning] Orphans
List every .md and .html file under .lore/reference/, recursively — stratified wikis keep pages in category subdirectories. Exclude index.md and index.html. Any file not listed in the index is an orphan.
For each orphan, record its path.
[info] Changed or missing provenance
For each indexed wiki page, read its source metadata. Markdown pages use the fg-sources frontmatter field as a YAML list of relative paths. HTML pages use the fg-sources meta tag as a comma-separated or YAML-like list.
For each source path:
- Check whether the file exists on the filesystem.
- If it exists, its newer modification time may suggest a review, but is not evidence that the reference page is stale. Historical source edits do not establish current behavior.
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.
- 17d ago Changed · -5 lines 9af48405986e
- 1mo ago First seen · 114 lines · 55 tokens per session scan A 33470194a571
lint is a skill published in the GitHub repository rjroy/vibe-garden (6 stars, last pushed 18d ago), licensed MIT. It adds 55 tokens to every session and 1,088 once invoked, about $0.0002 per session on Opus 5.5. 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
pace-learn
A knowledge-management process that records reusable lessons and patterns from completed reviews, failed checks, rejected work, and signs of struggle.
pace-pulse
Auto-invoked during advance mode after extended work on same CR, at session start/end, or when rhythm anomalies are detected. NOT for metrics reports or retrospectives (use /pace-retro). NOT for project status overview (use /pace-status).
add-teams
Adds Microsoft Teams connector to a Power Apps code app. Use when sending Teams messages, posting to channels, or integrating with Teams chat.
sys-configure
Configure Claude Octopus — redirects to /octo:setup interactive wizard.
relations
OPS on-demand: This skill should be used when the user asks to "who do I owe a reply", "relationship…
llm-friendly-context
Clarifies inputs, outputs, success criteria, decisions, and unresolved conditions so downstream consumers can execute without guessing. Use when writing or revising LLM-facing prompts, handoffs, planning artifacts, reviews, reports, or generated instructions.