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 skills/isaacsight/kernel/teacher-trace-curationnpx skills add isaacsight/kernel --skill teacher-trace-curationgit clone --depth 1 https://github.com/isaacsight/kernelWrote 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/isaacsight/kernel/teacher-trace-curation)<a href="https://agentmods.dev/skills/isaacsight/kernel/teacher-trace-curation"><img src="https://agentmods.dev/badge/skills/isaacsight/kernel/teacher-trace-curation.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 | $0.00036 | $0.00653 |
| Opus 5 | $0.00018 | $0.00327 |
| Sonnet 5 | $0.00007 | $0.00131 |
| Haiku 4.5 | $0.00004 | $0.00065 |
Grade A, and why
teacher-trace-curation 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 yesterday.
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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Teacher Trace Curation
Every time kbot calls Claude, the prompt + response is written to ~/.kbot/teacher/traces.jsonl. Left alone, this is just a log. Curated, it's the dataset that teaches the local model to answer your questions without touching the API.
Iron Law
ONLY SUCCESSFUL, CORRECTED, AND USER-APPROVED TRACES ENTER THE DATASET.
Failed traces teach the model to fail. Garbage in is not "more data."
The Weekly Ritual
kbot train-self --mode default --max-examples 500 --iters 200 --num-layers 8— curates + fine-tunes in one pass. The curator runs first, scores traces, and writes~/.kbot/teacher/dataset-default.jsonl.- Review the top 50 entries in the dataset file. Skim titles + first 200 chars.
- Remove anything you wouldn't want the local model to imitate:
- Responses you corrected mid-session.
- Hallucinated library names or APIs.
- Advice you later decided was wrong.
- Re-run step 1 with the cleaned dataset if you made significant deletions.
- Test:
ollama run kernel-self:<timestamp>on a task from the last week. Compare against the Claude baseline.
For longer cycles of evaluation + retraining, use kbot train-cycle which chains curate → train → evaluate → merge across multiple iterations.
The Quality Signal That Matters Most
Was this answer used without correction? The curator scores partly on: no correction in the next 5 turns, no follow-up question asking for clarification, no user rephrasing. Approved-by-silence is the strongest endorsement.
What You're Actually Building
A local model that answers "how do I deploy this?" using your deploy flow, not Anthropic's generic best practice. Your infrastructure, your naming, your conventions, your past decisions. That's what the local model becomes over weeks.
Anti-Pattern
Training on everything. Larger datasets with noisy data fine-tune worse models than small curated datasets. 200 excellent examples beat 2,000 mediocre ones every time.
Integration
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.
- yesterday First seen · 55 lines · 36 tokens per session scan A b21ea46259ff
teacher-trace-curation is a skill published in the GitHub repository isaacsight/kernel (16 stars, last pushed 6d ago), licensed MIT. It adds 36 tokens to every session and 653 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
house-trainer
Operate the EP-T house-method QLoRA trainer end-to-end on the T480 eGPU — dataset builds (T2), training/eval/GGUF (T3+), verification, and the data-quality levers. Use when training, evaluating, rebuilding the dataset, verifying a T-task, or extending Workstream T.
data-auditor
Performs data auditing and generation of move-analysis validations over Pypes executions.
omni-inference
The core OpenAI-compatible inference endpoints: chat completions, embeddings, images, audio (TTS/STT), moderations, rerank, and the Responses API. The primary integration surface for AI agents.
omni-compression
Configure RTK (command output), Caveman (prose), and stacked compression modes. Manage language packs, custom rules, and test prompt compression reducing tokens by 60–90%.
cli-eval
Create and run evaluation suites, watch live benchmark progress, view scorecards, compare model performance, and integrate eval runs with CI workflows from the CLI.
cli-batches
Submit and monitor batch inference jobs from the CLI. Upload and manage files for batch processing, retrieve results, and integrate batch pipelines with CI/CD workflows.