boxel: Skill for Claude Code

.claude/skills/flaky-test-fix/SKILL.md

flaky-test-fix is a skill for Claude Code from cardstack/boxel. It costs 0 tokens per session (993 once invoked), scanned A, original, MIT.

A procedure for investigating and fixing an intermittent test failure reported by a continuous integration (CI) job or test name. It looks for earlier fixes, finds the underlying cause, and adds diagnostic information.

In plain words
What is it for?
Use it to trace a flaky test from a CI job link to a root-cause fix and useful failure logs.
Why use it?
Flaky tests pass and fail unpredictably, often hiding timing, ordering, or resource problems. This avoids masking the problem with retries, longer timeouts, or skipped tests.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is cardstack/boxel's own configuration. It tells Claude Code how to work on boxel 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 boxel configures →

Reuse

Borrowing it

Nothing to install: this file belongs to cardstack/boxel. 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/cardstack/boxel/main/.claude/skills/flaky-test-fix/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/cardstack/boxel

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 flaky-test-fix

README.md
[![agentmods](https://agentmods.dev/badge/skills/cardstack/boxel/flaky-test-fix/github.svg)](https://agentmods.dev/skills/cardstack/boxel/flaky-test-fix)
Your own site
<a href="https://agentmods.dev/skills/cardstack/boxel/flaky-test-fix"><img src="https://agentmods.dev/badge/skills/cardstack/boxel/flaky-test-fix/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 flaky-test-fix

Your own site · 80×15
<a href="https://agentmods.dev/skills/cardstack/boxel/flaky-test-fix"><img src="https://agentmods.dev/badge/skills/cardstack/boxel/flaky-test-fix.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 993 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 $0.00000 $0.00993
Opus 5.5 $0.00000 $0.00397
Sonnet 5.5 $0.00000 $0.00199
Haiku 4.5 $0.00000 $0.00099

Measured 3d ago against content hash db351fde4c66, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

flaky-test-fix 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 3d 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/flaky-test-fix/SKILL.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Flaky Test Fix

A flaky test reported by a CI URL is a request for five things, done in order: prior-art search → Linear issue → worktree → root-cause fix → diagnostic logging. Do not paper over the failure with a retry, an increased timeout, or a skip/todo unless the failure genuinely cannot be diagnosed without more data — and if so, lead with the diagnostics and say so explicitly.

Why this protocol

Flaky tests are uncertain by nature. A fix that looks correct in local repro often does not address the real race / ordering / resource issue that triggers it in CI. Two safeguards counter that:

  • Prior-art search catches the common case where the same test has been "fixed" before. Without that context you risk re-doing a fix that already proved insufficient, or undoing an intentional accommodation.
  • Diagnostic logging bundled with the fix means that if the fix misses the real root cause, the next CI failure produces enough signal to diagnose it — instead of burning another CI cycle staring at the same opaque output.

Procedure

1. Search for prior fix attempts first

Before touching anything, find out whether this test has been worked on before. Search by test name, file path, and failure signature:

gh search prs "<test name or file>"   # searches open + closed by default
gh pr list --state=all --search "<test name or failure signature>"
git log --oneline -- <path/to/test/file>

If you find a prior PR, read its description, diff, and review thread before designing your fix. You may be looking at a regression, a partial fix, or a class of flakiness someone has already characterized. Surface any prior attempts early so the reporter can weigh in if the new fix should look materially different from the last.

2. Create a Linear issue for the flaky test

Unless the reporter already names a ticket, recommend a Linear issue that tracks the flake, and create it once they agree. Search Linear for the test name first: an existing issue for the same flake is updated, not duplicated. Give a new issue these settings, and set the state of an existing issue too:

Read the full file on GitHub · 64 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. 3d ago Changed · +13 lines db351fde4c66
  2. 5d ago First seen · 51 lines · 0 tokens per session scan A 6a5fc9a436f5

Subscribe to this mod's changes

flaky-test-fix is a skill published in the GitHub repository cardstack/boxel (27 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 993 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 2026-10-21.

Related

Other skills, from other repositories

systematic-debugging

4-phase root cause debugging: understand bugs before fixing.

NousResearch/hermes-agent · 16 tokens

langsmith-observability

LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.

davila7/claude-code-templates · 45 tokens

experimental-code-coverage-local-debugger

Runs code coverage locally via Universal Test Runner (UTR) or helper scripts, mimicking LUCI trybots. Activate when CQ tryjobs fail or underreport coverage, to test local GN/recipe repairs before uploading, or to debug hermetic crashes.

chromium/chromium · 59 tokens

verify-omnigent

Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…

omnigent-ai/omnigent · 100 tokens

cli-e2e

Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.

ComposioHQ/composio · 62 tokens

adversarial-reviewer

Stress-test a code change for concrete correctness defects, unsafe assumptions, and failure modes. Use when the user explicitly asks for an adversarial review, a deep bug hunt, or to tear a change apart, or to check your own change before submitting it. Do not use for ordinary review, style feedback, or general…

emdash-cms/emdash · 72 tokens