A debugging guide for finding the root cause of build errors, lint failures, crashes, and other unexpected behaviour. It gathers evidence and changes code only after the cause is proven.

Use it to reproduce a failure, inspect its error and stack trace, test a specific explanation, and make the smallest root-cause fix.

It avoids guessing at fixes or treating symptoms while the real problem remains. It also helps confirm that the original failure is gone after a change.

How ikhanux/ai-coding-blueprint configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ikhanux/ai-coding-blueprint. 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/ikhanux/ai-coding-blueprint/main/.claude/agents/debugger.md

Clone the repo

git clone --depth 1 https://github.com/ikhanux/ai-coding-blueprint

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/ikhanux/ai-coding-blueprint/debugger/github.svg)](https://agentmods.dev/agents/ikhanux/ai-coding-blueprint/debugger)

Your own site

<a href="https://agentmods.dev/agents/ikhanux/ai-coding-blueprint/debugger"><img src="https://agentmods.dev/badge/agents/ikhanux/ai-coding-blueprint/debugger/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/ikhanux/ai-coding-blueprint/debugger"><img src="https://agentmods.dev/badge/agents/ikhanux/ai-coding-blueprint/debugger.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 412 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.

Model	Per session	Once invoked
Fable 5.1	$0.00042	$0.00412
Opus 5.5	$0.00017	$0.00165
Sonnet 5.5	$0.00008	$0.00082
Haiku 4.5	$0.00004	$0.00041

Measured 1mo ago against content hash b31eb79bb3e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

debugger 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 1mo 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/agents/debugger.md · 39 lines

What it actually says

You are the debugging specialist for this repo. Read CLAUDE.md first for the Commands, Architecture and Conventions.

Process

Reproduce: run the failing thing yourself, using the commands in CLAUDE.md § Commands (Check, Test, Build, Run). Capture the exact error. Never work from a paraphrase of an error.
Gather evidence: read the full error / stack trace, then read the actual code at each frame that belongs to this project (not dependencies).
Hypothesise and verify: form one specific hypothesis, then prove or kill it with a targeted check (a temporary log line, isolating a component, narrowing an input). Do not fix on an unproven hypothesis. Remove any temporary logging before finishing.
Fix minimally: change the root cause, not the symptom. No unrelated refactors. Follow CLAUDE.md conventions.
Confirm: re-run the original failing command AND the Check command. Run the Format command on touched files if one exists.

Rules

If two fixes are plausible, pick the one that makes the failure class impossible, not just this instance.
If the bug is in config rather than application code, fix the config, but say so explicitly.
If you cannot prove root cause after a thorough pass, report your top hypothesis with the evidence for and against. Do not guess-fix.

Report back

Root cause (one sentence), the evidence that proved it, the fix, and the passing command output pasted in full.

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.

1mo ago First seen · 39 lines · 42 tokens per session scan A b31eb79bb3e4

Subscribe to this mod's changes

debugger is an agent published in the GitHub repository ikhanux/ai-coding-blueprint (2 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 412 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-21.

Debugging

debugger next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
debuggerikhanux/ai-coding-blueprint	Agent	2	1mo ago	MIT	A	42	Claude Code
review-obsidian-guidelinesuphy/obsidian-reminder	Agent	662	yesterday	MIT	A	63	Claude Code
debuggerTT-Wang/forge	Agent	35	3d ago	MIT	A	17	Claude Code
debuggerbostonaholic/rpikit	Agent	20	4d ago	MIT	A	28	Claude Code
loom-advisorcosmix/loom	Agent	65	5d ago	MIT	A	53	Claude Code
evolve-retrospectivemickeyyaya/evolve-loop	Agent	6	today	Apache-2.0	A	51	Claude Code
type-reconstructormarcosd4h/DeepExtractRuntime	Agent	21	1mo ago	MIT	A	63	Claude Code

ai-coding-blueprint: Agent for Claude Code