analyze-test-failures

analyze-test-failures is a skill for Claude Code from Jamie-BitFlight/claude_skills. It costs 72 tokens per session (800 once invoked), scanned A, original, MIT.

A troubleshooting guide for investigating failed software tests and deciding whether the test or the application is at fault. It compares the test's intended behavior with the implementation.

In plain words
What is it for?
It helps inspect assertions, error messages, stack traces, and code paths when tests fail.
Why use it?
It prevents developers from treating every failure as a product bug or blindly changing a correct test. It separates incorrect expectations from real implementation problems.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Part of the dh plugin — 53 skills, 28 agents shipped together

Good fit It helps inspect assertions, error messages, stack traces, and code paths when tests fail.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jamie-bitflight/claude_skills/analyze-test-failures
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.

Any agent
npx skills add Jamie-BitFlight/claude_skills --skill analyze-test-failures
Clone the repo
git clone --depth 1 https://github.com/Jamie-BitFlight/claude_skills

Made for: Claude Code.

Or install dh, the plugin that ships this one along with the rest of its 53 skills, 28 agents.

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 analyze-test-failures

README.md
[![agentmods](https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/analyze-test-failures/github.svg)](https://agentmods.dev/skills/jamie-bitflight/claude_skills/analyze-test-failures)
Your own site
<a href="https://agentmods.dev/skills/jamie-bitflight/claude_skills/analyze-test-failures"><img src="https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/analyze-test-failures/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 analyze-test-failures

Your own site · 80×15
<a href="https://agentmods.dev/skills/jamie-bitflight/claude_skills/analyze-test-failures"><img src="https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/analyze-test-failures.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 800 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00072 $0.00800
Opus 5 $0.00036 $0.00400
Sonnet 5 $0.00014 $0.00160
Haiku 4.5 $0.00007 $0.00080

Measured 6d ago against content hash 7de14d9be03a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

analyze-test-failures 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.

plugins/development-harness/skills/analyze-test-failures/SKILL.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Analyze Test Failures

Analyze failing test cases with a balanced, investigative approach.

Context

When tests fail, there are two primary possibilities:

  1. False positive: The test itself is incorrect
  2. True positive: The test discovered a genuine bug

Analysis Process

1. Initial Analysis

  • Read the failing test carefully, understanding its intent
  • Examine the test's assertions and expected behavior
  • Review the error message and stack trace

2. Investigate the Implementation

  • Check the actual implementation being tested
  • Trace through the code path that leads to the failure
  • Verify that implementation matches documented behavior

3. Apply Critical Thinking

For each failing test, ask:

  • What behavior is the test trying to verify?
  • Is this behavior clearly documented or implied by the API design?
  • Does the current implementation actually provide this behavior?
  • Could this be an edge case the implementation missed?

4. Make a Determination

Classify the failure as one of:

Classification Meaning
Test Bug Test's expectations are incorrect
Implementation Bug Code doesn't behave as it should
Ambiguous Intended behavior is unclear

5. Document Reasoning

Provide clear explanation including:

  • Evidence supporting the conclusion
  • Specific mismatch between expectation and reality
  • Recommended fix (to test or implementation)

Example Analyses

Example 1: Ambiguous Behavior

Scenario: Test expects calculateDiscount(100, 0.2) to return 20, but it returns 80

Analysis:

  • Test assumes function returns discount amount
  • Implementation returns price after discount
  • Function name is ambiguous

Determination: Ambiguous Recommendation: Check documentation or clarify intended behavior

Example 2: Implementation Bug

Scenario: Test expects validateEmail("[email protected]") to return true, but it returns false

Read the full file on GitHub · 129 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 · 129 lines · 72 tokens per session scan A 7de14d9be03a

Subscribe to this mod's changes

analyze-test-failures is a skill published in the GitHub repository Jamie-BitFlight/claude_skills (66 stars, last pushed today), licensed MIT. It adds 72 tokens to every session and 800 once invoked, about $0.0004 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.

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

adversarial-reviewer

Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.

emdash-cms/emdash · 71 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

work

Deliver one maintainer-approved EmDash issue, choosing the bug-fix path for a defect and the direct implementation path for an enhancement or task.

emdash-cms/emdash · 31 tokens