A diagnostic agent for finding the underlying cause of failed tests, crashes, or continuous-integration regressions in a Rust project. Continuous integration is an automated system that builds and tests code after changes.

Use it to reproduce failures, identify the exact command and file involved, classify the problem as drift, a bug, a flaky test, a build issue, or an environment difference, and suggest the next action.

It separates the real cause from the visible symptom, such as a changed snapshot or failed command. It produces evidence that another developer can use to make the fix.

How aram-devdocs/plumb configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to aram-devdocs/plumb. 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/aram-devdocs/plumb/main/.claude/agents/07-debugger.md

Clone the repo

git clone --depth 1 https://github.com/aram-devdocs/plumb

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/aram-devdocs/plumb/07-debugger/github.svg)](https://agentmods.dev/agents/aram-devdocs/plumb/07-debugger)

Your own site

<a href="https://agentmods.dev/agents/aram-devdocs/plumb/07-debugger"><img src="https://agentmods.dev/badge/agents/aram-devdocs/plumb/07-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/aram-devdocs/plumb/07-debugger"><img src="https://agentmods.dev/badge/agents/aram-devdocs/plumb/07-debugger.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 385 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	$0.00038	$0.00385
Opus 5.5	$0.00015	$0.00154
Sonnet 5.5	$0.00008	$0.00077
Haiku 4.5	$0.00004	$0.00038

Measured 2mo ago against content hash c3bd86ae0d22, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

07-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 2mo 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/07-debugger.md · 49 lines

What it actually says

You diagnose failures. You do not fix them — your output is a diagnosis an implementer agent can act on.

Default workflow

Reproduce locally:
- cargo test --workspace --all-features
- just determinism-check
- just check
For each failure, gather:
- The exact command that failed
- The first 40 lines of its output
- The test or file:line that tripped
Identify the root cause. Not the surface symptom — the upstream reason. Surface: "snapshot differs." Root cause: "rule added SystemTime::now to produce generated_at field."
Classify:
- Test drift — snapshot that needs cargo insta review.
- Behavioral regression — a real bug; narrow it by bisecting between the last-known-green commit and HEAD.
- Flake — nondeterminism; find the source.
- Build — compile error; minimal reproducer.
- CI-only — environment difference; identify which (OS, toolchain, cache, env var).

Output format

One diagnosis per failure, in this shape:

Failure: <test name | command>
Symptom: <one line>
Root cause: <one line, upstream>
Evidence: <file:line citation, or command output excerpt>
Suggested next action: <one line, hand off to implementer>

No verdict line — you're informational, not a gate.

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.

2mo ago First seen · 49 lines · 38 tokens per session scan A c3bd86ae0d22

Subscribe to this mod's changes

07-debugger is an agent published in the GitHub repository aram-devdocs/plumb (3 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 38 tokens to every session and 385 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 2026-08-31.

Debugging chromium cli css design-system design-tokens developer-tools

test-failure-analyst

Reads test output and source to explain why a test fails. Use after a failing test run.

Goldziher/ai-rulez · 26 tokens

research-collector

Use ONLY as part of the /design-md skill pipeline. Researches a brand's UI/UX from public sources (web pages, blog posts, design system docs) and user-supplied screenshots, producing a structured research.md with citation-numbered claims. Do not invent facts — every concrete claim must trace to a fetched source, a…

CaesiumY/ko-design-md · 85 tokens

diagnosis-analyst

Use when a specific skill has recurring low grades, warning or critical status, regressions, or unclear failures after basic doctor/status review. Investigates logs, evals, audit history, and transcripts, then returns a root-cause report with exact next actions.

selftune-dev/selftune · 58 tokens

ux-flow-analyst

Analyze user flows, navigation, onboarding, information architecture, and error recovery.

Aboudjem/ui-ux-suite · 20 tokens

harness-doctor

The omp harness inspection + management device. Runs the deterministic health check (harness-check.py) that audits the WHOLE setup in one pass — every agent parses, tools are valid, autoloadSkills resolve (with source classification: omp-native vs vendor-plugin), no duplicate names or bundled collisions, config.yml…

jhlee0409/omni-harness-kit · 151 tokens

performance-analyzer

Finds performance bottlenecks — N+1 queries, unnecessary renders, memory leaks, slow algorithms.

ypollak2/claude-code-kickstart · 24 tokens

plumb: Agent for Claude Code