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 usemoss/moss --skill moss-pikachugit clone --depth 1 https://github.com/usemoss/mossWrote 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/usemoss/moss/moss-pikachu)<a href="https://agentmods.dev/skills/usemoss/moss/moss-pikachu"><img src="https://agentmods.dev/badge/skills/usemoss/moss/moss-pikachu/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/usemoss/moss/moss-pikachu"><img src="https://agentmods.dev/badge/skills/usemoss/moss/moss-pikachu.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 | $0.00080 | $0.00710 |
| Opus 5.5 | $0.00032 | $0.00284 |
| Sonnet 5.5 | $0.00016 | $0.00142 |
| Haiku 4.5 | $0.00008 | $0.00071 |
Grade A, and why
moss-pikachu 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 1mo 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Moss Pikachu Agent Skill
Project docs (start here)
| Doc | Purpose |
|---|---|
| project-summary.md | Full technical reference |
| how-to.md | End-user guide |
| contribution.md | Contributor guide |
Specialized skills
| Skill | Use when |
|---|---|
| moss-pikachu-semantic-search | Search quality, query tuning |
| moss-pikachu-indexing | Indexing, manual/automatic modes |
| moss-pikachu-contributing | PRs and contribution workflow |
Read order
Non-negotiables
- Xcode
.appbundle — not a root-level SPM executable for the menu bar app - macOS-only target —
SUPPORTED_PLATFORMS = macosx - Python worker for Moss on macOS — Moss Swift SPM is iOS-only
pip install moss>=1.6.0— GitHubmainsdks/python/sdklacksSessionIndexAPI- No hardcoded credentials —
MOSS_PROJECT_ID/MOSS_PROJECT_KEYvia Keychain or env - NSPanel for search overlay — not
WindowGroup(avoids Dock icon)
Phase gates
Run before advancing phases:
./.cursor/skills/moss-pikachu/scripts/validate-phase.sh 1
./.cursor/skills/moss-pikachu/scripts/validate-phase.sh 2
./.cursor/skills/moss-pikachu/scripts/validate-phase.sh 3
Task sequencing
| Phase | Scope |
|---|---|
| 1 | Menu bar, hotkey, search overlay shell, settings window |
| 2 | FileMonitor, moss_worker.py, MossBridge, SearchService |
| 3 | Pikachu animations, live search UI, settings, polish |
Do not wire live search before MossBridge + SearchService compile and pass Phase 2 validation.
Code conventions
@MainActorfor all UI updatesasync/awaitfor MossBridge calls (not callbacks)- Line-delimited JSON between Swift and Python (
\nterminated) - Debounce FSEvents (100ms) and search input (200ms)
MARK:sections in Swift service files
What ships with it
7 files 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.
- 1mo ago First seen · 72 lines · 80 tokens per session scan A fd2e7e2a67d7
moss-pikachu is a skill published in the GitHub repository usemoss/moss (798 stars, last pushed today), licensed BSD-2-Clause. It adds 80 tokens to every session and 710 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
rag-expert
Design retrieval-augmented generation systems: chunking, embeddings, vector and hybrid search, reranking, grounding and evaluation. Use when the user mentions RAG, retrieval, semantic search, embeddings, vector databases, pgvector, Chroma, Qdrant, Pinecone, chunking or reranking, wants an assistant answering over…
rag-retrieval-audit
Diagnose missing evidence in a RAG pipeline with labeled queries, chunk/trace inspection, Recall@K/MRR/nDCG, and stage-isolated failure taxonomy. Use when retrieval looks fine but answers fail, or when index/chunk/filter/rerank changes need before/after proof.
Hybrid Search Architect
Designs a hybrid retrieval pipeline combining dense vector search and BM25 sparse search with reciprocal rank fusion, and explains when to use each configuration.
molecular-rag
Retrieve structurally similar compounds with known properties from ChEMBL/ZINC to ground predictions and inform optimization. Based on MolRAG (Xian 2025, ACL).
nemotron-retrieval-recipes
Use when planning, debugging, tuning, evaluating, exporting, or deploying public Nemotron embed/rerank retrieval recipes.
memex-search
Discover prior agent work across sessions, projects, providers, and machines. Use for historical investigations and analogous solutions, or as a fallback when native conversation and history tools cannot recover the needed evidence.