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 lightninglabs/wavelength --skill doc-gardeninggit clone --depth 1 https://github.com/lightninglabs/wavelengthWrote 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/lightninglabs/wavelength/doc-gardening)<a href="https://agentmods.dev/skills/lightninglabs/wavelength/doc-gardening"><img src="https://agentmods.dev/badge/skills/lightninglabs/wavelength/doc-gardening/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/lightninglabs/wavelength/doc-gardening"><img src="https://agentmods.dev/badge/skills/lightninglabs/wavelength/doc-gardening.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00065 | $0.01047 |
| Opus 5 | $0.00032 | $0.00524 |
| Sonnet 5 | $0.00013 | $0.00209 |
| Haiku 4.5 | $0.00006 | $0.00105 |
Grade A, and why
doc-gardening 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 9d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Doc Gardening
Maintain the per-package documentation graph after code changes. This skill handles both generating docs for new packages and updating stale docs for existing ones.
If $ARGUMENTS is a specific package path (e.g., round or lib/tree),
scope work to that package only. If $ARGUMENTS is all or empty, scan the
entire repo.
Phase 1: Detect Changes
Determine what needs attention.
For scoped runs (specific package):
- Read the package's
.gofiles and existingCLAUDE.md(if any). - Determine if new or stale.
For full runs (all or no argument):
# Find packages missing CLAUDE.md
find . -name '*.go' -not -path './.git/*' -not -path './vendor/*' \
-not -path './tools/*' | sed 's|/[^/]*$||' | sort -u | while read dir; do
[ ! -f "$dir/CLAUDE.md" ] && echo "MISSING: $dir"
done
# Find packages with Go changes on current branch
git diff --name-only main...HEAD -- '*.go' | sed 's|/[^/]*$||' | sort -u
Classify each affected package:
- New — has
.gofiles but noCLAUDE.md. - Stale — has
CLAUDE.mdbut Go source changed since last update.
Phase 2: Read Package Sources
For each affected package, gather:
doc.go(if exists) — package purpose.- Key exported types and interfaces (read primary
.gofiles, usego doc). - Import statements — which repo packages it imports.
README.md(if exists) — existing deep docs to link.- Actor message flows — search for Tell/Ask calls, outbox message types,
FSM event types, and
lib/actormsgmarker interfaces that cross package boundaries. List concrete Go type names for each send/receive direction.
Use the Explore agent for packages with many files, or direct Read/Grep for small packages. Be thorough — per-package docs must be accurate, not guessed.
Message tracing tips:
- Search for
Tell(andAsk(calls to find outbound messages. - Search for types implementing
VTXOActorMsg,RoundReceivable, or otherlib/actormsgmarker interfaces to find cross-boundary message types. - Check FSM transition functions for outbox event types (emitted as side effects).
- Check
EventRouterdispatch registrations inserverconnfor ingress routing.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 111 lines · 65 tokens per session scan A 76b09069cc22
doc-gardening is a skill published in the GitHub repository lightninglabs/wavelength (46 stars, last pushed today), licensed MIT. It adds 65 tokens to every session and 1,047 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…