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 moonlight-lupin/agent-skills --skill skill-retrievalgit clone --depth 1 https://github.com/moonlight-lupin/agent-skillsWrote 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/moonlight-lupin/agent-skills/skill-retrieval)<a href="https://agentmods.dev/skills/moonlight-lupin/agent-skills/skill-retrieval"><img src="https://agentmods.dev/badge/skills/moonlight-lupin/agent-skills/skill-retrieval/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/moonlight-lupin/agent-skills/skill-retrieval"><img src="https://agentmods.dev/badge/skills/moonlight-lupin/agent-skills/skill-retrieval.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 | $0.00081 | $0.01749 |
| Opus 5 | $0.00041 | $0.00874 |
| Sonnet 5 | $0.00016 | $0.00350 |
| Haiku 4.5 | $0.00008 | $0.00175 |
Grade A, and why
skill-retrieval 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 2d 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Retrieval
This is a Hermes Agent plugin. It is not a Claude Code plugin and will
not load in Claude Code — that runtime has no pre_llm_call event, no Python
register() entry point, and reads .claude-plugin/plugin.json rather than
plugin.yaml. Developed against Hermes Agent >=0.20.0.
BM25-based progressive disclosure for Hermes Agent skills. Instead of dumping every skill description into the system prompt (~11.5K tokens), this plugin keeps a compact names-only index and injects only the top-K relevant descriptions per turn.
What it does
Two-phase progressive disclosure:
-
Phase 1 — System prompt compaction (session start): Monkey-patches
build_skills_system_promptso the<available_skills>block lists skill names only (descriptions stripped). All skills remain discoverable by name (~2K tokens instead of ~11.5K). -
Phase 2 — Per-turn BM25 retrieval (
pre_llm_callhook): Tokenizes the user message, ranks active skill descriptions with BM25 Okapi, and injects the top-K matches (~300 tokens) as context above the user message.
Architecture
Session start
│
▼
Phase 1: patch build_skills_system_prompt
└── <available_skills> → names only (~2K tokens)
Each turn (pre_llm_call)
│
▼
Phase 2: BM25Index.retrieve(user_message, top_k)
└── inject "## Retrieved Skills ..." into user message (~300 tokens)
The BM25 index is built once at plugin load from standalone skills
(~/.hermes/skills) and plugin-bundled skills (~/.hermes/plugins/*/skills).
Retrieval uses a pure-stdlib inverted index (term → posting list of
precomputed BM25 weights) and is sub-millisecond for ~200 skills.
Token savings
| Stage | Tokens (approx.) |
|---|---|
| Before (full skill list in system prompt) | ~11.5K |
| After — names-only system prompt | ~2.0K |
| After — per-turn top-K descriptions | ~0.3K |
| Net per turn | ~2.3K (~9K saved) |
Measured on a Hermes install with ~300 skills; savings scale with skill count.
What ships with it
12 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.
- __init__.py 12 KB runs code
- LICENSE 2.4 KB
- plugin.yaml 477 B
- README.md 1.9 KB
- requirements-dev.txt 78 B
- requirements.txt 12 B
- scripts/bm25_retriever.py 26 KB runs code
- tests/conftest.py 188 B runs code
- tests/test_bm25_retriever.py 15 KB runs code
- tests/test_issue8_round2.py 13 KB runs code
- tests/test_regressions.py 25 KB runs code
- tests/test_stdlib_parity.py 11 KB runs code
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.
- 2d ago Changed 546368feb9b4
- 10d ago First seen · 176 lines · 81 tokens per session scan A 6d6fd9dafedd
skill-retrieval is a skill published in the GitHub repository moonlight-lupin/agent-skills (60 stars, last pushed 3d ago), licensed MIT. It adds 81 tokens to every session and 1,749 once invoked, about $0.0004 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
SoloFlow
A meta-skill that silently watches your workflows and automatically generates reusable Hermes skills from them.
hermes-tweet
Use Xquik in Hermes Agent for public X research, monitoring, thread summaries, creator discovery & approved actions. Not affiliated with X Corp. Use when the user requests X data or a named action. Trigger with "search X", "monitor X", "post tweet", or "X trends".
image
Create or optimize marketing images, social graphics, product mockups, banners, cover art, listing visuals, brand assets, image prompts, WebP files, and OG images.
video
Plan and produce video with available AI tools or programmatic frameworks. Use for video prompts, avatars, explainers, demos, templates, pipelines, and generation.
content-analysis
Analyze articles, documents, videos, podcasts, and transcripts for arguments, evidence, themes, assumptions, contradictions, insights, and unanswered questions.
content-research-writer
Research, outline, draft, cite, and revise articles, reports, tutorials, newsletters, and case studies with traceable sources and preserved voice.