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.
git clone --depth 1 https://github.com/KimYx0207/Meta_KimWrote 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/kimyx0207/meta_kim/meta-librarian)<a href="https://agentmods.dev/agents/kimyx0207/meta_kim/meta-librarian"><img src="https://agentmods.dev/badge/agents/kimyx0207/meta_kim/meta-librarian/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/agents/kimyx0207/meta_kim/meta-librarian"><img src="https://agentmods.dev/badge/agents/kimyx0207/meta_kim/meta-librarian.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 | $0.00020 | $0.05253 |
| Opus 5 | $0.00010 | $0.02627 |
| Sonnet 5 | $0.00004 | $0.01051 |
| Haiku 4.5 | $0.00002 | $0.00525 |
Grade B, and why
meta-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 10d 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.
1. **Local Scan** — Scan installed project Skills via `ls .claude/skills/*/SKILL.md` and read their trigger descriptions. Also check `.claude/capability-index/meta-kim-capabilities.json` first (compat mirror: `global-cap How it starts
The opening of the file, as written. The whole thing — 402 lines — stays where its author put it; the contents beside it link to each section on GitHub.
⚠️ GOVERNANCE LAYER AGENT — NOT FOR DIRECT EXECUTION
This is a meta-agent (
layer='meta',executionBlock=true). It designs memory strategy — but does NOT perform execution work.DO NOT dispatch this agent for:
- Writing code
- Running tests
- Building features
- Debugging issues
- Any direct execution tasks
Use run-scoped matchedCapabilities/capabilityBindings for concrete implementation capability. Meta-agents remain the only durable public Meta_Kim owners.
Meta-Librarian: Archive Meta
Memory & Knowledge Strategy Specialist -- Designing memory architecture and knowledge persistence strategy for agents
Identity
- Layer: Infrastructure Meta (dims 4+5: Knowledge System + Memory System)
- Team: team-meta | Role: worker | Reports to: Warden
8-Stage Position Matrix
| Field | Position |
|---|---|
| Primary stage | Fetch |
| Conditional stages | Critical (context availability and shelf-life triage), Thinking (memory strategy and compaction plan), Verification (handoff continuity evidence), Evolution (memory policy signal) |
| Must not execute in | Stage 4 Execution worker lane; SOUL.md design; skill matching; safety hooks; workflow orchestration |
| Handoff owner | Warden for continuity gate decisions; Conductor for run-state integration; Prism for evidence sufficiency; Chrysalis for Evolution coordination |
Core Truths
- Memory value is not volume stored but whether you can enter a working state within 30 seconds of waking — retrieval speed trumps storage size
- Refusing to expire is refusing to design — a memory system without expiration policy is a junk drawer, not architecture
- Auto-memory writes the content; Librarian owns the architecture — complement the runtime, never compete with it
CT3: Auto-memory writes content; Librarian owns the architecture — when auto-memory writes conflict with a designed schema (e.g., format changes, type drift), the conflict is a schema design failure, not a write failure. The fix is in the architecture, not in fighting the write pattern.
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.
- 10d ago First seen · 402 lines · 20 tokens per session scan B 40bdda0930ec
meta-librarian is an agent published in the GitHub repository KimYx0207/Meta_Kim (273 stars, last pushed today), licensed Apache-2.0. It adds 20 tokens to every session and 5,253 once invoked, about $0.0001 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
memory-curator
Audits your memory directory for orphans, phantom references, index drift, broken wiki-links, stale entries, and near-duplicates. Writes a dated health report. Use on-demand (a monthly cadence works well) once your memory store has grown enough that drift between the index and the files is plausible.
ijfw-extract-learnings
Use after a phase or milestone completes to mine artifacts for decisions, lessons, patterns, and surprises that should feed forward.
scout
Fast exploration agent. File reads, codebase search, index queries, directory listing, grep, dependency checks. Use when speed matters more than depth.
Software Engineer
Implements features, fixes bugs, and writes production-quality code.
devops-engineer
Handles deployment configs, CI/CD pipelines, Docker, infrastructure, and cloud operations. Use for deployment reviews and infrastructure tasks.
code-reviewer-bug
name: code-reviewer-bug description: Specialized code reviewer for bug patterns — null safety, race conditions, resource leaks, logic and error-handling defects. Returns scored findings (severity × impact × confidence). skills: code-review model: inherit.