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 agentmods add skills/luna-prompts/skillnote/skill-pushnpx skills add luna-prompts/skillnote --skill skill-pushgit clone --depth 1 https://github.com/luna-prompts/skillnoteWhat 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 | $0.00050 | $0.01294 |
| Opus 5 | $0.00025 | $0.00647 |
| Sonnet 5 | $0.00010 | $0.00259 |
| Haiku 4.5 | $0.00005 | $0.00129 |
Grade A, and why
skill-push scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
import urllib.request, json, os How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Push
Create and push reusable skills to the SkillNote registry so every connected agent learns from repeated patterns.
Resolve the host
HOST=$(cat ~/.skillnote/host 2>/dev/null | tr -d '[:space:]'); HOST=${HOST:-localhost}
API="http://${HOST}:8082"
(In Python: host = (open(os.path.expanduser('~/.skillnote/host')).read().strip() if os.path.exists(os.path.expanduser('~/.skillnote/host')) else 'localhost').)
When to Act
- The user gave the same instruction or convention 2+ times this session.
- The user explicitly asks to create, save, or push a skill.
- Session retrospective — review for saveable patterns before wrapping up.
Only suggest for PERSISTENT conventions, not temporary workarounds.
Step 1: Confirm (REQUIRED — never skip)
If the user did not explicitly ask to create a skill, you MUST ask first. Tell the user what you noticed in one sentence, then ask: "Want me to save this as a SkillNote skill?" Wait for an explicit yes before drafting anything.
Skip this step only when the user already said "create a skill for X" / "save this pattern" / "push a skill" in their own words.
Step 2: Draft
Collaborate on three fields:
- name: lowercase letters, hyphens, digits; max 64 chars. Also the slug.
- description (max 1024 chars — THIS IS THE TRIGGER): what the skill does + explicit trigger keywords. Agents pick a skill based solely on its description.
- content: instructions under ~200 lines, starting with
# Title, actionable with examples.
Show the full draft to the user.
Step 3: Check if it exists
import urllib.request, json, os
host = open(os.path.expanduser('~/.skillnote/host')).read().strip() if os.path.exists(os.path.expanduser('~/.skillnote/host')) else 'localhost'
api = f"http://{host}:8082"
try:
resp = urllib.request.urlopen(f"{api}/v1/skills/<SLUG>")
print(f"EXISTS: v{json.loads(resp.read()).get('current_version', '?')}")
except urllib.error.HTTPError as e:
print("NEW" if e.code == 404 else f"ERROR: {e.code}")
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.
- 3d ago First seen · 112 lines · 50 tokens per session scan A 0f9bca5c55f7
skill-push is a skill published in the GitHub repository luna-prompts/skillnote (59 stars, last pushed 19d ago), licensed MIT. It adds 50 tokens to every session and 1,294 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
promptscript
PromptScript language expert for reading, writing, modifying, and troubleshooting .prs files. Use when working with PromptScript syntax, creating or editing .prs files, adding blocks like @identity, @standards, @restrictions, @shortcuts, @skills, or @agents, configuring promptscript.yaml, resolving compilation errors…
thesis-control
Use when AI-assisted thesis edits risk claim drift, scope creep, loss of author control, or repeated revisions that fail to converge; provides spine cards, edit contracts, drift audits, revision escalation, and human gates.
helius-jupiter
Skill "helius-jupiter" from helius-labs/core-ai, covering helius x jupiter — build defi apps on solana, mcp router surface, prerequisites, 1. helius mcp server and 2. jupiter api key.
argument-governance
Build and audit the manuscript argument system: intent, gap-contribution alignment, hierarchical claims, evidence balance, limitations, and reviewer attack surfaces. Use when a paper, thesis chapter, review article, or rebuttal needs explicit intent registers, contribution chains, claim hierarchy, argument maps…
verify
Fact-check claims encountered during reading — dates, names, events, citations. Use when encountering historical facts or disputed claims.
map
Show or update the mapping between literature and thesis chapters — which sources support which arguments. Use for tracking coverage.