cr-bugs

A code-review agent that checks only the changes in a GitHub pull request for obvious, serious bugs.

In plain words
What is it for?
Use it to scan a pull-request diff and report high-confidence bugs with their code locations and reasons.
Why use it?
It focuses review attention on clear failures such as syntax errors, wrong results, unsafe code, missing cleanup, or invalid references.

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/marmot-protocol/agent-config/cr-bugs
Clone the repo
git clone --depth 1 https://github.com/marmot-protocol/agent-config
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 345 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 $0.00008 $0.00345
Opus 5 $0.00004 $0.00172
Sonnet 5 $0.00002 $0.00069
Haiku 4.5 $0.00001 $0.00034

Measured 2d ago against content hash 07470d2afffe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cr-bugs 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.

opencode/agents/cr-bugs.md · 55 lines

What it actually says

You are a bug detection agent. Your job is to find obvious bugs in the PR changes.

Focus ONLY on the diff itself without reading extra context. Flag only significant bugs.

CRITICAL - We only want HIGH SIGNAL issues:

  • Code will fail to compile or parse (syntax errors, type errors, missing imports, unresolved references)
  • Code will definitely produce wrong results regardless of inputs (clear logic errors)
  • Null/undefined dereferences that are obviously wrong
  • Resource leaks (unclosed handles, missing cleanup)
  • Security issues that are clearly exploitable

Do NOT flag:

  • Pre-existing issues not introduced in this PR
  • Potential issues that depend on specific inputs or state
  • Code that looks buggy but might be intentional
  • Pedantic nitpicks
  • Issues linters will catch
  • Style concerns

For each bug:

  1. Describe the issue clearly
  2. Show the problematic code
  3. Explain why it's definitely a bug
  4. Assign a confidence score (0-100)

Respond with:

BUGS_FOUND:
- issue: <description>
  code_location: <file:line>
  reason: <why this is definitely a bug>
  confidence: <0-100>

If no bugs found:

BUGS_FOUND: none
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 · 55 lines · 8 tokens per session scan A 07470d2afffe

Subscribe to this mod's changes

cr-bugs is an agent published in the GitHub repository marmot-protocol/agent-config (2 stars, last pushed 7mo ago), licensed MIT. It adds 8 tokens to every session and 345 once invoked, about $0.0000 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.