flake-to-fact

flake-to-fact is a skill for Claude Code, Codex from lancewillett/ai-plugins. It costs 77 tokens per session (785 once invoked), scanned A, original, MIT.

A method for classifying intermittent or recurring failures using observed evidence, a specific cause, and a confidence level instead of calling everything “flaky.”

In plain words
What is it for?
Use it to triage test, build, deployment, performance, security, or CI failures and produce more precise incident reports.
Why use it?
It keeps the failure description separate from assumptions about its cause and identifies what diagnostic evidence is still missing.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the flake-to-fact plugin — 1 skill shipped together

Good fit Use it to triage test, build, deployment, performance, security, or CI failures and produce more precise incident reports.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lancewillett/ai-plugins/flake-to-fact
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 lancewillett/ai-plugins --skill flake-to-fact
Clone the repo
git clone --depth 1 https://github.com/lancewillett/ai-plugins

Made for: Claude Code, Codex.

Or install flake-to-fact, the plugin that ships this one along with the rest of its 1 skill.

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 flake-to-fact

README.md
[![agentmods](https://agentmods.dev/badge/skills/lancewillett/ai-plugins/flake-to-fact.svg)](https://agentmods.dev/skills/lancewillett/ai-plugins/flake-to-fact)
Your own site
<a href="https://agentmods.dev/skills/lancewillett/ai-plugins/flake-to-fact"><img src="https://agentmods.dev/badge/skills/lancewillett/ai-plugins/flake-to-fact.svg" alt="Measured on agentmods" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 785 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 $0.00077 $0.00785
Opus 5 $0.00039 $0.00392
Sonnet 5 $0.00015 $0.00157
Haiku 4.5 $0.00008 $0.00078

Measured 7d ago against content hash 0aef441ebff9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

flake-to-fact 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 7d 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/flake-to-fact/skills/flake-to-fact/SKILL.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Flake to fact

Apply the core rules below. When file tools are available, read the taxonomy for detailed classifications and examples. Classify the failure, not the test or the people involved.

Workflow

  1. Capture observed facts first: the exact failing signature, failed step or assertion, relevant logs, execution context, and run history. Keep facts separate from inferences.
  2. Describe recurrence separately from cause. Use intermittent only when the same signature has both passed and failed in comparable runs. Omit it for a one-off failure, even when the mechanism is commonly intermittent or the source calls it flaky or nondeterministic. It is a modifier, never a root cause.
  3. Choose the narrowest supported domain, mechanism, and scope from the taxonomy. State all three in the label or expanded report. For step 6's Unclassified fallback, use Unclassified instead of a domain and omit the mechanism rather than guessing.
  4. State confidence from the evidence:
    • High: direct error, trace, or reproduction identifies the mechanism.
    • Medium: several consistent signals identify the likely mechanism.
    • Low: the signature or context suggests a domain, but a distinguishing diagnostic is missing.
  5. Treat retries as measurement, not proof. A passing retry can establish recurrence; it cannot prove the failure was harmless or identify its cause.
  6. If evidence cannot support a mechanism, write: Unclassified [intermittent ]failure: <exact signature>; needs <specific diagnostic>. Include intermittent only with comparable pass/fail evidence. Do not invent a cause.

Label and output

Default to one plain-English line:

[Intermittent ]<domain>—<specific mechanism failure>: <exact signature or affected scope>

Examples: Test environment—database startup failure: MySQL container did not become healthy and Test design—brittle selector failure: visible-text lookup no longer matches the control.

For an expanded report, use this order:

Read the full file on GitHub · 51 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 7d ago First seen · 51 lines · 77 tokens per session scan A 0aef441ebff9

Subscribe to this mod's changes

flake-to-fact is a skill published in the GitHub repository lancewillett/ai-plugins (2 stars, last pushed 22d ago), licensed MIT. It adds 77 tokens to every session and 785 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 2026-08-31.

Related

Other skills, from other repositories

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

systematic-debugging

Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.

open-metadata/OpenMetadata · 37 tokens

diagnose

Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.

emdash-cms/emdash · 43 tokens

repro-admin

Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.

emdash-cms/emdash · 48 tokens

log-error-digest

Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…

zebbern/claude-code-guide · 71 tokens

byted-util-volcengine-detect-retry

An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.

bytedance/agentkit-samples · 101 tokens