flisk: Skill for Claude Code

.claude/skills/layer-autoresearch/SKILL.md

layer-autoresearch is a skill for Claude Code from flisk-sh/flisk. It costs 92 tokens per session (1,041 once invoked), scanned A, original, MIT.

An experiment procedure for changing Flisk's Docker build layers and keeping changes that reduce memory used by idle services.

In plain words
What is it for?
Use it for contributor-only experiments on Docker layer generators, measuring container memory, and keeping or discarding each trial.
Why use it?
It provides a controlled way to compare layer changes while protecting the main branch and preserving features.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is flisk-sh/flisk's own configuration. It tells Claude Code how to work on flisk itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything flisk configures →

Reuse

Borrowing it

Nothing to install: this file belongs to flisk-sh/flisk. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/flisk-sh/flisk/main/.claude/skills/layer-autoresearch/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/flisk-sh/flisk

Made for: Claude Code.

Wrote 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.

agentmods badge for layer-autoresearch

README.md
[![agentmods](https://agentmods.dev/badge/skills/flisk-sh/flisk/layer-autoresearch/github.svg)](https://agentmods.dev/skills/flisk-sh/flisk/layer-autoresearch)
Your own site
<a href="https://agentmods.dev/skills/flisk-sh/flisk/layer-autoresearch"><img src="https://agentmods.dev/badge/skills/flisk-sh/flisk/layer-autoresearch/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.

agentmods 80×15 button for layer-autoresearch

Your own site · 80×15
<a href="https://agentmods.dev/skills/flisk-sh/flisk/layer-autoresearch"><img src="https://agentmods.dev/badge/skills/flisk-sh/flisk/layer-autoresearch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,041 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00092 $0.01041
Opus 5.5 $0.00037 $0.00416
Sonnet 5.5 $0.00018 $0.00208
Haiku 4.5 $0.00009 $0.00104

Measured 5d ago against content hash 75f660a10f13, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

layer-autoresearch 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 5d 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.

.claude/skills/layer-autoresearch/SKILL.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Layer autoresearch

Adapted from karpathy/autoresearch program.md. You are an autonomous researcher making the Flisk runtime layers cheaper without removing features.

Setup (with the user, once)

  1. Agree a run tag (e.g. sep25). Create git checkout -b autoresearch/<tag> from main. The branch must be new.
  2. Ask the user whether any tool auto-commits or pushes working-tree edits in this checkout. If one does, ask them to pause it for the run (or run from a separate git worktree), because experiment commits and resets must not reach origin/main.
  3. Read the in-scope files in full:
    • Editable: runtime/engine/topologies/platform/docker/layers/*.star, runtime/engine/topologies/platform/docker/layers/prisma/*.star, runtime/engine/topologies/platform/docker/build/golden_image_dockerfile.star, runtime/engine/topologies/platform/docker/config/healthcheck.star.
    • Read-only ground truth: scripts/autoresearch/layer-eval.sh, scripts/benchmark/container-scale.ts, tests/tilt-engine/test_runtime_container_footprint.py, and any spec for the runtime container footprint under openspec/.
  4. The eval needs a Flisk project with at least LAYER_EVAL_SAMPLE (default 20) services. It uses FLISK_BENCH_PROJECT, or ../flisk-erp-system next to the checkout when that is unset. If neither exists, ask the user to clone the ERP scale-test project (about 100 services) once with flisk project erp --path ../flisk-erp-system (the eval generates and builds what it needs; do not start all of it with flisk up), or to point FLISK_BENCH_PROJECT at another large project.
  5. Create an untracked autoresearch-results.tsv with the header commit mem_mib image_mib status description.
  6. Confirm with the user, then start.

Experiment

Run scripts/autoresearch/layer-eval.sh > run.log 2>&1 (about 5-10 minutes). Read the results with grep -A20 '^---' run.log.

  • Primary metric: mem_per_service_mib, lower is better. This is idle memory per real service in the bench project, and it is what limits 100 services on 16 GB.
  • Tie-breaker: if memory is within 0.5 MiB of the best, a lower unique_per_service_mib or service_image_mib wins, then simpler code.
  • Hard constraints. status: ok requires all 20 services healthy, zero crashes, and passing feature tests. Anything else is a discard, or a crash if it didn't run.
  • Never edit the eval harness, benchmark, tests or spec. Never remove a user-facing feature: Prisma, Infisical entrypoint, hugo-as-feature, healthchecks, signal handling. Don't add dependencies.

Read the full file on GitHub · 54 lines

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. 5d ago First seen · 54 lines · 92 tokens per session scan A 75f660a10f13

Subscribe to this mod's changes

layer-autoresearch is a skill published in the GitHub repository flisk-sh/flisk (54 stars, last pushed yesterday), licensed MIT. It adds 92 tokens to every session and 1,041 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-11-15.

Related

layer-autoresearch compared with skills from other repositories

layer-autoresearch next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
layer-autoresearchflisk-sh/fliskSkill54yesterdayMITA92Claude Code
harborav/harborSkill3.3k9d agoApache-2.0A114Claude Code
docker-local-buildkurtosis-tech/kurtosisSkill559todayApache-2.0A56Claude Code, Codex
k8s-dev-deploykurtosis-tech/kurtosisSkill559todayApache-2.0A78Claude Code, Codex
docker-debugkurtosis-tech/kurtosisSkill559todayApache-2.0A45Claude Code, Codex
k8s-clean-clusterkurtosis-tech/kurtosisSkill559todayApache-2.0A59Claude Code, Codex
k8s-debug-podskurtosis-tech/kurtosisSkill559todayApache-2.0A62Claude Code, Codex