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 agentmods add commands/noah-sheldon/ai-dev-kit/learn-evalgit clone --depth 1 https://github.com/noah-sheldon/ai-dev-kitWhat 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 | $0.00012 | $0.00071 |
| Opus 5 | $0.00006 | $0.00036 |
| Sonnet 5 | $0.00002 | $0.00014 |
| Haiku 4.5 | $0.00001 | $0.00007 |
Grade A, and why
learn-eval 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 2d 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.
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.
What it actually says
Learn Eval
Turn an eval result into reusable guidance.
Delegate
Apply the eval-harness skill.
Notes
- Keep the workflow bounded and explicit.
- Keep responses short and direct.
- Prefer the maintained skill surface over duplicated prompt logic.
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.
- 2d ago First seen · 18 lines · 12 tokens per session scan A 980730b87f4a
learn-eval is a command published in the GitHub repository noah-sheldon/ai-dev-kit (13 stars, last pushed 4mo ago), licensed MIT. It adds 12 tokens to every session and 71 once invoked, about $0.0001 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 commands, from other repositories
agentlas-connect
Connect Agentlas agents or teams to Telegram.
agentlas-search
Search Agentlas Cloud and Hub agent candidates without invoking.
auto
Intent-classified router, the front door to OrchestKit and the DEFAULT entry point for any goal-shaped request. Classifies a plain-English goal and routes it to the right specialist skill. Routing is never overhead, so use it even when the target skill seems obvious; skip only when already executing inside another…
node-skill
Generate a Claude skill for a ComfyUI custom node pack.
autonomy_service
Tools to manage AI agents minted in the {{ autonolasprotocol }}.
blackboard
Read or write a Network-AI blackboard key (shared multi-agent state).