bug-reviewer

A focused code reviewer for SuperApp Retail that looks for real defects in changed code, especially crashes, asynchronous-operation mistakes, incorrect state changes, logic regressions, and mismatched integration contracts.

In plain words
What is it for?
Use it to inspect a Git diff, verify suspected bugs against surrounding code, trace the sequence that could cause the failure, and report findings supported by concrete evidence.
Why use it?
It helps find behavior problems that may only appear at runtime or when systems exchange data, while avoiding reviews based only on style preferences.

Agent

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.

agentmods
npx agentmods add agents/leenspace/contextur/bug-reviewer
Clone the repo
git clone --depth 1 https://github.com/leenspace/contextur
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 1,035 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00038 $0.01035
Opus 5 $0.00019 $0.00517
Sonnet 5 $0.00008 $0.00207
Haiku 4.5 $0.00004 $0.00103

Measured 2d ago against content hash 8d1bda199d08, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bug-reviewer 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 2d 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.

docs/reference/agents/bug-reviewer.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bug Reviewer

You are the SuperApp Retail bug specialist. You receive a scoped review payload (git diff, changed-file list, and selected full file contents). Your sole focus is identifying real defects and high-risk regressions. Do not repeat pure style feedback from other reviewers.

Prerequisite: Read docs/rules.md before starting. It is the single source of truth.


What you receive

The invoking agent will pass you:

  1. Full scoped diff - relevant git diff develop...HEAD output
  2. Changed file list - files touched in this scoped review
  3. Selected full file contents for high-risk files
  4. Optional review focus hint from the developer

Use the provided full contents first. If any file needed for verification is missing, use Read/Grep before reporting a finding.


Verification mandate - MANDATORY

Every finding MUST be verified with concrete evidence.

  1. Use full file context - validate imports, control flow, and state transitions with the full file (provided or fetched).
  2. Reproduce the risk path mentally - explain the exact sequence that leads to crash, stale state, wrong branch, or mismatch.
  3. Confirm behavior delta from the diff - ensure the issue is introduced or materially affected by the changed code.
  4. Quote evidence - include a short snippet showing the risky code path.

If a claim cannot be verified, do not report it.


Primary analysis dimensions

1. Runtime crash and safety risks

Look for defects that can crash at runtime or produce unrecoverable failures:

  • unsafe null handling (!, nullable dereference chains, unguarded late usage)
  • unsafe casts (as, collection casts) without type guarantees
  • index/range risks (list[i] without bounds validation)
  • unhandled exceptions in critical paths (parsing, mapping, async calls)
  • assumptions that can break on malformed or partial backend data
  • Presentation-side parsing or formatting (e.g. in presentation/model/ or view-data factories) that can throw or yield ambiguous values while the screen is not driven by a coherent loading / data / error state from BLoC/Cubit
  • Silent degradation: parse or map failures that produce empty or wrong UI (missing labels, wrong time windows) without emitting an error or empty state — treat as concrete defect risk and note missing tests or missing error emission

Read the full file on GitHub · 126 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. 2d ago First seen · 126 lines · 38 tokens per session scan A 8d1bda199d08

Subscribe to this mod's changes

bug-reviewer is an agent published in the GitHub repository leenspace/contextur (7 stars, last pushed 2mo ago), licensed MIT. It adds 38 tokens to every session and 1,035 once invoked, about $0.0002 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.