log-experiment

A command for recording the results of the latest software experiment in an experiments folder. It saves the changed solution, benchmark log, result summary, and lessons learned.

In plain words
What is it for?
Use it after benchmarking to create or update an experiment record with pass counts, latency, accuracy errors, descriptions, and reusable lessons.
Why use it?
It keeps experiment outcomes in a consistent history, including failed attempts. This makes it easier to compare runs and avoid repeating work.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/dogacel/auto-gpu-kernel/log-experiment
Clone the repo
git clone --depth 1 https://github.com/Dogacel/auto-gpu-kernel

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 427 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00427
Opus 5 $0.00000 $0.00214
Sonnet 5 $0.00000 $0.00085
Haiku 4.5 $0.00000 $0.00043

Measured 2d ago against content hash 6a43de3f6af3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

log-experiment 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.

dsa_sparse_attention_h16_ckv512_kpe64_topk2048_ps64/.claude/commands/log-experiment.md · 45 lines

What it actually says

/log-experiment

Log the most recent experiment. Never skip — failures are as valuable as wins.

Pick folder

List experiments/exp_*/. Let N = highest number.

  • If exp_N/plan.md exists without result.md → use exp_N/.
  • Else → create exp_(N+1)/.
  • No folders yet → exp_1/.

Never overwrite an existing result.md. If you'd have to, stop and ask the user.

Write artifacts

  1. Copy solution/triton/sparse_fused.py into the folder (same filename).
  2. Copy the Modal log produced by /benchmark to bench.log in the folder.
  3. Write result.md:
# Experiment N — YYYY-MM-DD

**Description:** what changed, why. Reference `plan.md` when implementing one.

## Results
- Pass: X/Y
- Kernel latency (ms): small=S.SSS / large=L.LLL / overall=O.OOO (min / median / max)
- Reference latency (ms): R.RRR
- Max abs err: X.XXe-X  |  Max rel err: X.XXe-X
- Mode: quick | stride N | full  (| ab-vs-exp_K if A/B)

## Learnings
What was learned. What to try or avoid next. If durable cross-experiment insight, also append one line to `experiments/LESSONS.md`.
  1. Append to experiments/summary.md (create with header row if missing):
| Exp | Date | Description | Latency | Ref | Pass | Notes |
|---|---|---|---|---|---|---|
| N | YYYY-MM-DD | one phrase | O.OOO ms | R.RRR ms | X/Y | Δ% vs prior best, "new best" / "regression" / "ablation" |

Keep Notes terse. Detail lives in result.md.

Changes

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.

  1. 2d ago First seen · 45 lines · 0 tokens per session scan A 6a43de3f6af3

Subscribe to this mod's changes

log-experiment is a command published in the GitHub repository Dogacel/auto-gpu-kernel (157 stars, last pushed 11d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 427 tokens. 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.