evidence-first-debugging

evidence-first-debugging is a skill for Claude Code from Caxson/proof-of-work. It costs 77 tokens per session (418 once invoked), scanned A, original, Apache-2.0.

A debugging guide that requires checking logs, code, real data, and a reproduction before deciding why something failed. It ranks possible causes by the evidence supporting them.

In plain words
What is it for?
Use it for failures, bugs, freezes, crashes, and other cases where it is unclear why something does not work. It helps investigate the evidence, test competing explanations, and fix the underlying cause.
Why use it?
It helps prevent guesses, premature blame of the environment, and fixes that hide symptoms while leaving the real bug in place.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the proof-of-work plugin — 2 skills, 3 commands, 1 hook shipped together

Good fit Use it for failures, bugs, freezes, crashes, and other cases where it is unclear why something does not work. It helps investigate the evidence, test competing explanations, and fix the underlying cause.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/caxson/proof-of-work/evidence-first-debugging
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 Caxson/proof-of-work --skill evidence-first-debugging
Clone the repo
git clone --depth 1 https://github.com/Caxson/proof-of-work

Made for: Claude Code.

Or install proof-of-work, the plugin that ships this one along with the rest of its 2 skills, 3 commands, 1 hook.

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 evidence-first-debugging

README.md
[![agentmods](https://agentmods.dev/badge/skills/caxson/proof-of-work/evidence-first-debugging.svg)](https://agentmods.dev/skills/caxson/proof-of-work/evidence-first-debugging)
Your own site
<a href="https://agentmods.dev/skills/caxson/proof-of-work/evidence-first-debugging"><img src="https://agentmods.dev/badge/skills/caxson/proof-of-work/evidence-first-debugging.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 418 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 $0.00418
Opus 5 $0.00039 $0.00209
Sonnet 5 $0.00015 $0.00084
Haiku 4.5 $0.00008 $0.00042

Measured 8d ago against content hash f8ae61a3b474, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

evidence-first-debugging 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 8d 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.

skills/evidence-first-debugging/SKILL.md · 38 lines

What it actually says

Evidence-First Debugging

Diagnosis is evidence, not guessing.

Rules

  1. Read the logs / code first. Never state "it fails because X" before you have read the relevant logs and code. No log read → no conclusion.

  2. Suspect yourself first. Default hypothesis: your own code, logic, or angle is wrong — not the environment, permissions, or hardware. Rule out your own bug with evidence before blaming anything external. (Classic trap: retrying your own broken input code, then blaming "permissions" and quitting.)

  3. One story, not many. A different "cause" each turn means you are guessing. Stop and return to the evidence.

  4. Rank hypotheses with evidence. List candidate causes, each with the specific evidence that confirms or refutes it and a confidence level. Do not commit to a fix until the top hypothesis is supported by data.

  5. Fix the root, not the symptom. Solve the actual mechanism (e.g. "incomplete data"), not the single field the log printed. Never delete data or run on a degraded state just to make the error disappear — that creates new bugs downstream.

Leverage

Dispatch an INDEPENDENT subagent to investigate noisy areas or to adversarially challenge your conclusion. A fresh perspective is the fastest way out of "I kept ramming my own wrong assumption." For broad log/grep sweeps, offload to a subagent and keep only the findings in main context.

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. 8d ago First seen · 38 lines · 77 tokens per session scan A f8ae61a3b474

Subscribe to this mod's changes

evidence-first-debugging is a skill published in the GitHub repository Caxson/proof-of-work (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 77 tokens to every session and 418 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