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 xg-gh-25/SwarmAI --skill s_librarygit clone --depth 1 https://github.com/xg-gh-25/SwarmAIWrote 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/xg-gh-25/swarmai/s_library)<a href="https://agentmods.dev/skills/xg-gh-25/swarmai/s_library"><img src="https://agentmods.dev/badge/skills/xg-gh-25/swarmai/s_library/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/xg-gh-25/swarmai/s_library"><img src="https://agentmods.dev/badge/skills/xg-gh-25/swarmai/s_library.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 | $0.00136 | $0.00811 |
| Opus 5 | $0.00068 | $0.00405 |
| Sonnet 5 | $0.00027 | $0.00162 |
| Haiku 4.5 | $0.00014 | $0.00081 |
Grade A, and why
library 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 today.
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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Library Skill — mount, search
The Library is the agent's bookshelf: the Native store (Knowledge/, already in
recall) + mount points — references to external directories on the user's disk,
indexed in place, never copied (index-not-warehouse). This skill is the
agent-facing half of the mount engines (the +Add Folder button uses the same core
functions via the API).
Core principle: a mount stores a {path, kind} pointer + an index,
never a copy of the source. Recall lands on the pointer → you Read the LIVE
source (progressive load). An external directory is mounted; a single file
goes to the Inbox (not this skill); a URL goes to s_learn-content.
Tool
python3 {SKILL_DIR}/scripts/library.py <command> [options]
All commands operate on the real library_mounts registry + the same
core.library_mounts engines the API uses — this skill does NOT reinvent them.
Commands
mount — register + index an external directory
Judge the kind from the directory (code if it holds parseable source, else docs), register it, and index:
python3 {SKILL_DIR}/scripts/library.py mount --path ~/Desktop/AI-Native/some-repo --scope SwarmAI
- code dir → builds a per-mount symbol graph (index in place). Done — symbols are now recallable.
- docs dir → chunks every UTF-8 text file straight into the shared Knowledge
FTS5 (same engine as
Knowledge/itself), so recall reaches it IMMEDIATELY. Binaries are skipped. No briefing step — mounting IS indexing.
search — see what recall would retrieve
python3 {SKILL_DIR}/scripts/library.py search --query "widget scoring" --scope SwarmAI
Runs the real recall path (library + codeintel domains) — the same thing the Browse-tab search box shows.
list — show registered mounts + health
python3 {SKILL_DIR}/scripts/library.py list --scope SwarmAI
Workflow — "mount "
- Run
mount --path <path>→ it judges kind, registers, AND indexes in one step (code → symbol graph; docs → text chunked into the shared Knowledge FTS5). - Confirm to the user: what was mounted, its kind, and the count indexed (symbols for code, chunks for docs) — recall reaches it immediately.
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.
- today Changed 7167254314fe
- 12d ago First seen · 68 lines · 136 tokens per session scan A df750cc109b8
library is a skill published in the GitHub repository xg-gh-25/SwarmAI (44 stars, last pushed today), licensed MIT. It adds 136 tokens to every session and 811 once invoked, about $0.0007 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
remember
Routes user requests containing "remember", "recall", "checkpoint", "session", "todo", or "where were we" to the correct OpenEmpiric (OEM) MCP tool. Use when the user wants to persist, retrieve, or contextualize knowledge from project memory.
why
Explain the provenance, authority, expiry, degradation state, and token accounting of CIGAR context already presented in this session.
checkpoint
Create an inspectable CIGAR checkpoint before compaction, interruption, or a meaningful task boundary.
memo-bank-query
Load the governing spec/contract for a file or topic from a project's memo-bank (a read-only MCP docs corpus) BEFORE reading code or editing. Use this in any repo that has a .island-slices.json or a memo-bank MCP server, whenever you are about to edit a file, or are asked "what governs X", "is there a spec for Y"…
audit-knowledge
Scan Antigravity conversation transcript + artifact directory for extractable knowledge. Use when user asks for 'knowledge audit', 'audit knowledge', 'check for extractable knowledge', 'scan transcript', or at session start when audit cadence is exceeded.
handoff
Generate a passoff package so the next reader can pick up cleanly — for future-you in a new session (typically when context is high and you need to restart) or for a coworker (via brief mode). Default + auto modes emit a paste-ready next-session opener as the headline artifact, alongside PROGRESS / CLAUDE / memory…