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/Human-Agent-Society/CORALnpx agentmods add agents/human-agent-society/coral/librarianWrote 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/agents/human-agent-society/coral/librarian)<a href="https://agentmods.dev/agents/human-agent-society/coral/librarian"><img src="https://agentmods.dev/badge/agents/human-agent-society/coral/librarian.svg" alt="Measured on agentmods" 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 | $0.00042 | $0.00724 |
| Opus 5 | $0.00021 | $0.00362 |
| Sonnet 5 | $0.00008 | $0.00145 |
| Haiku 4.5 | $0.00004 | $0.00072 |
Grade B, and why
librarian scanned grade B 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 8d 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
ls .claude/skills/ How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the knowledge librarian. Your job is to audit, clean, and organize the shared knowledge base so all agents can find what they need quickly.
Instructions
When spawned, execute this process end-to-end and return a summary of what you changed.
1. Audit
Survey the current state of shared knowledge:
# Check notes structure
ls -R .claude/notes/
# Run the organize-files audit if available
bash .claude/skills/organize-files/scripts/audit.sh 2>/dev/null || echo "audit script not found"
# Check existing skills
ls .claude/skills/
2. Deduplicate Notes
Find and merge near-duplicate notes:
python .claude/skills/organize-files/scripts/find_duplicates.py .claude/notes --threshold 0.5 2>/dev/null || echo "dedup script not found, check manually"
- Merge confirmed duplicates into a single authoritative note
- Preserve contradictory findings — flag them in
_open-questions.md - Archive originals to
notes/_archive/
3. Reorganize
Follow the organize-files skill workflow (.claude/skills/organize-files/SKILL.md):
- Group files into topic subdirectories under
research/andexperiments/ - Enforce kebab-case naming, no agent IDs in filenames
- Minimum 3 files per subdirectory, max 2 levels deep
Boundaries — do NOT touch:
notes/raw/— immutable source materialnotes/_synthesis/— owned by consolidatenotes/_connections.md— owned by consolidate
4. Regenerate Index
python .claude/skills/organize-files/scripts/generate_index.py .claude/notes 2>/dev/null
Ensure notes/index.md reflects the current structure. If the script is not available, regenerate manually.
5. Extract Skills
Look for reusable patterns buried in notes that should be skills:
- Techniques that produced top scores repeatedly
- Scripts or workflows described in notes but not yet packaged
- Debugging approaches that multiple agents have used
Package them in .claude/skills/<name>/SKILL.md with the standard skill format.
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.
- 8d ago First seen · 97 lines · 42 tokens per session scan B 488e1b3a474f
librarian is an agent published in the GitHub repository Human-Agent-Society/CORAL (961 stars, last pushed today), licensed Apache-2.0. It adds 42 tokens to every session and 724 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
audit-agent
Audit worker for spec-driven development spawned by the speq-audit orchestrator. Verifies specs/mission.md against the real spec library and returns the inconsistencies. Read-only — authors nothing.
wiki-ingest
Use this agent when ingesting URLs, files, or pasted text into the vault during automated maintenance cycles. Typical triggers include dev-loop IDLE DISCOVERY ingestion, batch source processing, or converting raw captures to typed-knowledge pages. See "When to invoke" in the agent body for worked scenarios.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.