Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/luna-prompts/skillnotenpx agentmods add skills/luna-prompts/skillnote/collectionWrote 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/luna-prompts/skillnote/collection)<a href="https://agentmods.dev/skills/luna-prompts/skillnote/collection"><img src="https://agentmods.dev/badge/skills/luna-prompts/skillnote/collection/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/luna-prompts/skillnote/collection"><img src="https://agentmods.dev/badge/skills/luna-prompts/skillnote/collection.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 39 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 55 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Agent Snooping · line 8 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Data Exfiltration · line 46 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00039 | $0.00685 |
| Opus 5.5 | $0.00016 | $0.00274 |
| Sonnet 5.5 | $0.00008 | $0.00137 |
| Haiku 4.5 | $0.00004 | $0.00068 |
Grade A, and why
collection scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sf "${API}/v1/collections" 2>/dev/null || echo "[]" How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SkillNote Collection Manager
Help the user choose which skill collection syncs into this project. The choice is stored in ./.skillnote.json; the plugin's sync hook materializes that collection's skills into ./.codex/skills/ on the next prompt.
Resolve the host
HOST=$(cat ~/.skillnote/host 2>/dev/null | tr -d '[:space:]'); HOST=${HOST:-localhost}
API="http://${HOST}:8082"
Step 1: Fetch collections
curl -sf "${API}/v1/collections" 2>/dev/null || echo "[]"
Step 2: Present the choices
Codex has no multiple-choice tool, so present a clear numbered list in plain text and ask the user to reply with a number or name. Build the list in this order:
- Recommended first: if
basename($PWD)(lowercased, non-alphanumerics →-) matches an existing collection name, list it first and mark it· recommended. - All other existing collections as
<name> — <count> skills. Mark the currently-active one (from./.skillnote.json) with(current). Create a new collection…Skip (no skills synced)
Then ask: "Which collection should this project use? (reply with a number or name)" and wait for the reply.
Step 3: Apply the selection
Existing collection
echo '{"collections": ["<SELECTED_NAME>"]}' > ./.skillnote.json
rm -f ./.codex/skills/.last-sync-time # force an immediate re-sync on the next prompt
Tell the user: "Switched to . Your skills refresh on your next message — or type /skills after a moment."
Create a new collection
Ask for a name in plain text. Validate: must match ^[a-z0-9_-]+$, 1–128 chars, and must not contain anthropic or claude. Re-prompt once if invalid. Then:
curl -sf -X POST "${API}/v1/collections" \
-H "Content-Type: application/json" \
-d '{"name": "<NAME>", "description": ""}'
If curl returns 409, the collection already exists — offer to activate it instead. On success, write it to ./.skillnote.json and reset the sync throttle exactly as above.
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.
- 1mo ago First seen · 64 lines · 39 tokens per session scan A 31e92d020ca9
collection is a skill published in the GitHub repository luna-prompts/skillnote (66 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 685 once invoked, about $0.0002 per session on Opus 5.5. 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
confluence-property
Manage content properties (custom metadata) on Confluence pages and blog posts. ALWAYS use for custom metadata, key-value data, or application-specific fields.
confluence-search
Search Confluence using CQL queries, validate syntax, export results, and manage search history. ALWAYS use when user wants to find, search, or query for content.
confluence-comment
Manage comments on Confluence pages - add, get, update, delete, and resolve comments. ALWAYS use for feedback, discussions, and inline annotations.
confluence-space
Manage Confluence spaces - create, list, update, delete, and configure spaces. ALWAYS use when user wants to work with spaces (not individual pages).
confluence-watch
Content watching and notifications. ALWAYS use when user wants to follow content or manage notifications.
confluence-hierarchy
Navigate and manage Confluence page hierarchies, ancestors, descendants, and trees. ALWAYS use for parent/child relationships and page tree navigation.