keel-pilot

keel-pilot is a skill for Claude Code from muratsilahtaroglu/claude-code-starter-kit. It costs 57 tokens per session (1,153 once invoked), scanned A, original, MIT.

A staged safety process for jobs that produce many outputs, such as labels, generated files, or data transformations. It checks a small sample and defined quality targets before allowing the full job to run.

In plain words
What is it for?
Use it for bulk labeling, classification, content generation, migrations, or other unattended jobs with more than about 100 outputs.
Why use it?
It helps catch a bad pipeline before it creates thousands of incorrect results. It also defines when to stop if errors rise during the larger run.

Skill for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: mentions subagents.

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 skills/muratsilahtaroglu/claude-code-starter-kit/keel-pilot
Any agent
npx skills add muratsilahtaroglu/claude-code-starter-kit --skill keel-pilot
Clone the repo
git clone --depth 1 https://github.com/muratsilahtaroglu/claude-code-starter-kit

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 keel-pilot

README.md
[![agentmods](https://agentmods.dev/badge/skills/muratsilahtaroglu/claude-code-starter-kit/keel-pilot.svg)](https://agentmods.dev/skills/muratsilahtaroglu/claude-code-starter-kit/keel-pilot)
Your own site
<a href="https://agentmods.dev/skills/muratsilahtaroglu/claude-code-starter-kit/keel-pilot"><img src="https://agentmods.dev/badge/skills/muratsilahtaroglu/claude-code-starter-kit/keel-pilot.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,153 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 5.1 $0.00057 $0.01153
Opus 5 $0.00028 $0.00576
Sonnet 5 $0.00011 $0.00231
Haiku 4.5 $0.00006 $0.00115

Measured 6d ago against content hash 840ef806ae1d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

keel-pilot 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 6d 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/keel-pilot/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/keel-pilot — never run a big batch blind

Use when a task will produce many outputs whose quality cannot be eyeballed one by one — mass labeling/classification, bulk generation, large migrations/transforms (heuristic: >100 items, or any unattended run). The failure this kills: pipelines verified "sometimes, by mood" — quality problems discovered after 5,000 items, or never. The sequence below is the published norm, not an invention (Anthropic best-practices fan-out, Pangakis et al. 2023, SRE canarying, Write-Audit-Publish); evidence trail with sources: research/*/findings.md (2026-07-16).

Five gates, in order. A gate must PASS before the next opens — report each as pass/fail.

Gate 0 — DECLARE (before anything runs)

Write into the task (TASKS.md done-when: or a short pilot plan next to the runner):

  • acceptance metrics — e.g. per-class precision/recall vs a gold set; schema-validity %;
  • halt thresholds for the full run — e.g. >5% schema-invalid, or error rate >2× the pilot's, in any rolling 100-item window → HALT;
  • sample plan — smoke size (10–50) · gold set (250+ human-labeled items when label quality is load-bearing; smaller only with the user's explicit OK) · honeypot rate (5–10%) · acceptance sample by the rule of three (0 errors in 60 ⇒ <5% true error rate, in 300 ⇒ <1%, at 95%). Thresholds chosen AFTER seeing outputs are not thresholds. Defaults above are the literature's — adjust per project, with the user.

Gate 1 — SMOKE (10–50 items)

Run the pipeline end-to-end on 10–50 representative items, edge cases included. Human eyeball + mechanical schema check (fields present, types right, label ∈ allowed set). Any surprise → fix, re-smoke. Never skip to Gate 3 because "the code looks right".

Gate 2 — VALIDATE (against ground truth)

Run on the gold set; compare per class (aggregate accuracy hides minority-class failure — median GPT-4 accuracy across 27 real tasks was 0.850 while a third of tasks had precision or recall below 0.5). Agreement bar: Krippendorff α ≥ 0.800 to rely on labels; 0.667–0.800 supports only tentative conclusions. Below bar → revise prompt/config and re-run THIS gate. Record the passing numbers in reports/ (dated) — they are the baseline the circuit breaker compares against.

Read the full file on GitHub · 66 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. 6d ago First seen · 66 lines · 57 tokens per session scan A 840ef806ae1d

Subscribe to this mod's changes

keel-pilot is a skill published in the GitHub repository muratsilahtaroglu/claude-code-starter-kit (9 stars, last pushed 2d ago), licensed MIT. It adds 57 tokens to every session and 1,153 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

autonomous-loops

Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.

affaan-m/ECC · 26 tokens

mle-workflow

Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.

affaan-m/ECC · 44 tokens

react-patterns

React 18/19 patterns including hooks discipline, server/client component boundaries, Suspense + error boundaries, form actions, data fetching, state management decision trees, and accessibility-first composition. Use when writing or reviewing React components.

affaan-m/ECC · 49 tokens

content-engine

Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content calendars, or one source asset adapted cleanly across platforms.

affaan-m/ECC · 55 tokens

article-writing

Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.

affaan-m/ECC · 57 tokens

agent-carnet

Use this skill when the user asks to save, recall, find, or organize notes. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check the notebook', 'find in carnet'. Also use proactively when discovering findings worth preserving across sessions.

yamadashy/repomix · 67 tokens