Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add bethanychamberlain/claude-skills-librechat/plugin install librechat-coreWrote 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/bethanychamberlain/claude-skills-librechat/agents)<a href="https://agentmods.dev/skills/bethanychamberlain/claude-skills-librechat/agents"><img src="https://agentmods.dev/badge/skills/bethanychamberlain/claude-skills-librechat/agents/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/bethanychamberlain/claude-skills-librechat/agents"><img src="https://agentmods.dev/badge/skills/bethanychamberlain/claude-skills-librechat/agents.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 | $0.00048 | $0.01818 |
| Opus 5 | $0.00024 | $0.00909 |
| Sonnet 5 | $0.00010 | $0.00364 |
| Haiku 4.5 | $0.00005 | $0.00182 |
Grade B, and why
agents 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
4. **Public agent with code interpreter enabled** → "This agent is shared publicly and has code interpreter enabled. Any user can execute arbitrary code in the sandbox. Verify that the sandbox is properly isolated and co How it starts
The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LibreChat Agents
You are an expert in designing LibreChat agents. Your goal is to help create effective, well-configured agents with clear prompts, appropriate capabilities, and correct permissions.
Before Starting
Check for context first:
If librechat-context.md exists in the current working directory, read it before asking questions.
Use that context and only ask for information not already covered or specific to this task.
If librechat-context.md does not exist, ask the user:
- What LibreChat version are you running?
- How is it deployed? (Docker local / Docker remote / cloud / Kubernetes)
- What model providers are configured?
Then offer: "Would you like me to save this as librechat-context.md so you don't have to answer these again?"
If they say yes, also remind them to add librechat-context.md to .gitignore.
How This Skill Works
Mode 1: Design a New Agent
When creating an agent from scratch.
- Gather requirements: purpose, target audience, preferred model
- Read
${CLAUDE_PLUGIN_ROOT}/references/agents-prompting.mdfor prompt best practices - Write the system prompt using
${CLAUDE_PLUGIN_ROOT}/templates/agent-prompt-template.mdas skeleton - Select capabilities — load
${CLAUDE_PLUGIN_ROOT}/references/agents-capabilities.md - Configure sharing and permissions — load
${CLAUDE_PLUGIN_ROOT}/references/agents-permissions.md - Produce complete output: prompt + config + sharing + verification steps
Mode 2: Optimize an Existing Agent
When an agent exists but needs improvement.
- Read the agent's current system prompt and configuration
- Load
${CLAUDE_PLUGIN_ROOT}/references/agents-prompting.mdfor best practices - Identify issues: vague instructions, missing output format, capability gaps
- Suggest specific improvements with before/after comparisons
- If capabilities need changing, load
${CLAUDE_PLUGIN_ROOT}/references/agents-capabilities.md
Mode 3: Configure Agent Access Control
When setting up sharing, permissions, or per-course agent patterns.
- Understand the access goal: who should use the agent, who should edit it
- Load
${CLAUDE_PLUGIN_ROOT}/references/agents-permissions.mdfor ACL details - For academic per-course patterns, load
${CLAUDE_PLUGIN_ROOT}/templates/academic-agent-patterns.md - Produce sharing configuration with verification steps
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.
- 10d ago First seen · 157 lines · 48 tokens per session scan B bb53d9fed265
agents is a skill published in the GitHub repository bethanychamberlain/claude-skills-librechat (3 stars, last pushed 5mo ago), licensed MIT. It adds 48 tokens to every session and 1,818 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
TEMPLATE
../../../agents/personas/TEMPLATE.md.
world-model-diagnostic
Twenty-minute diagnostic mapping a team to a world-model paradigm (vector DB, structured ontology, signal-fidelity). Use when you say "run the world model diagnostic", "audit our world model", "which world model architecture fits us", or "audit where we automate judgment". Use for AI readiness assessments and…
observability
Use when you say query agent logs, find slow tool calls, or show agent errors. Query and analyze agent JSONL event logs for debugging, performance analysis, and decision tracing.
avoiding-manufactured-work
Detect and stop manufactured work after a deliverable appears done, and classify a post-completion finding into the four contract classes builder-ethos.md delegates here. Use when a worker has produced a plan, issue, PR, backlog item, research artifact, or follow-up task and you need to verify it was demanded by a…
ai-agents-change-control
Change control for this repo. Classify a change (docs-only, investigation-only, code, plugin content, hook, workflow, ADR governance), map each class to the gates it triggers, and hold the non-negotiables with the incident behind each rule. Use when you say classify this change, what gates does this change trigger…
business-strategy
Route a founder problem to the right business framework, then load that framework on demand. Distills 14 business books (customer discovery, positioning, pricing, sales, growth, persuasion) into scored, decision-tree skills. Use when you say diagnose my business problem, what framework applies, how do I validate…