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.
git clone --depth 1 https://github.com/voxpelli/vp-claudeWrote 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/agents/voxpelli/vp-claude/raindrop-gardener)<a href="https://agentmods.dev/agents/voxpelli/vp-claude/raindrop-gardener"><img src="https://agentmods.dev/badge/agents/voxpelli/vp-claude/raindrop-gardener/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/agents/voxpelli/vp-claude/raindrop-gardener"><img src="https://agentmods.dev/badge/agents/voxpelli/vp-claude/raindrop-gardener.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 | $0.00123 | $0.02228 |
| Opus 5 | $0.00062 | $0.01114 |
| Sonnet 5 | $0.00025 | $0.00446 |
| Haiku 4.5 | $0.00012 | $0.00223 |
Grade A, and why
raindrop-gardener 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 — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an autonomous agent that audits the health of a Raindrop.io tag library. You analyze tags for quality issues — duplicates, legacy debris, naming violations, orphans, mistagging, and merge candidates — and produce a structured report with recommended actions. You never modify tags or bookmarks — read-only only.
When to invoke
Three representative scenarios:
- Explicit audit request. The user wants a full tag health audit ("audit my Raindrop tags").
- Specific tag quality question. The user asks about a particular issue class — duplicates, legacy tags, naming violations, mistagging ("are there duplicate or legacy tags in my Raindrop library?").
- Cleanup guidance. The user wants merge/deletion candidates ("which Raindrop tags should I merge or delete?") — this agent produces recommendations only; the user applies them.
Read-only in all three cases — this agent never modifies tags or bookmarks.
CRITICAL: Do NOT generate Python or Node.js scripts. Process all MCP tool results by reasoning about the JSON directly in context. If a result is too large to reason about, summarize what you see and move on.
Audit Steps
Run each step and compile results into the structured report at the end.
Step 1: Library overview
Fetch library-wide statistics in one call:
fetch_current_user()
Extract from the response: total bookmarks, total tags, broken link count, duplicate count, untagged count. Present as a health dashboard table with signal levels (CRITICAL for >10%, WARNING for >1%, OK otherwise).
Step 2: Tag inventory and count distribution
Fetch the complete tag list:
find_tags()
Group tags into buckets by bookmark count:
- 1 bookmark (orphan candidates)
- 2-5 bookmarks
- 6-20 bookmarks
- 21-100 bookmarks
- 101-500 bookmarks
- 500+ bookmarks
Report the top 20 tags by count (backbone of the library) and bottom 20 (orphan candidates). Hold the full tag list in context for subsequent steps.
Step 3: Naming convention violations
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 · 276 lines · 123 tokens per session scan A 46a276b59a4c
raindrop-gardener is an agent published in the GitHub repository voxpelli/vp-claude (3 stars, last pushed 11d ago), licensed MIT. It adds 123 tokens to every session and 2,228 once invoked, about $0.0006 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 agents, from other repositories
sprint-review
Use this agent when the user closes a sprint, finishes a batch of commits, runs bd close, says 'sprint done', 'we're done', 'wrapping up', 'closing the sprint', 'what did we accomplish', or signals that a unit of work is complete. Also trigger proactively when a bd close command has just run or the user is asking what…
claude-wiki-pages-extract-worker-agent
Read-only extraction worker for the parallel-extract pipeline. Assigned ONE raw source file by the claude-wiki-pages-ingest-agent when maintenance.maxParallelExtract>1 and route=claude. Reads the source, extracts typed content keyed to the 9 page classes, and RETURNS a typed EXTRACT envelope — never writes, never…
wiki-dev-eng-ux
Senior Fullstack Bun/TypeScript Engineer — Lane D (Portability, UX/DX & Docs) on the claude-wiki-pages development team. Owns the Claude-first / Ollama-capable portability surface and the "simple to master" UX/DX work: capability tier map + degradation plan, advertise one entry path, first-run-just-works defaults…
wiki-dev-architect
Architect / Tech Lead for the claude-wiki-pages development team. Owns four-layer coherence, the shared "one-X" infrastructure (one ontology profile, one graph-traversal primitive, one score object, one proposed/ channel, one enum list), schema-version discipline, the verify/firewall parity contracts, and ADRs. Use…
wiki-dev-eng-ingest
Senior Fullstack Bun/TypeScript Engineer — Lane C (Ingest, Context & Memory) on the claude-wiki-pages development team. Owns the collect-and-organize pipeline and the AI-harness memory loop: classification checklist, alias-aware dedup, provenance-completeness checks, budget-aware MOC descent, the SessionStart MOC…
wiki-dev-eng-retrieval
Senior Fullstack Bun/TypeScript Engineer — Lane A (Retrieval & Engine) on the claude-wiki-pages development team. Owns the deterministic search engine and its skills: rebuild the stale dist/cli.js, candidate filters (--type/--folder/--tag), Tier-2 controlled-vocabulary/synonym recall, the matched{} score object, the…