Find bugs in branch changes

Reviews the commits on the current branch for security holes, bugs and quality issues with an eleven-item checklist and reports verified findings with file, line, severity and fix, without editing code. Use when you want a security-first pass before a PR.

Code reviewPack: Sentry skills75 linesfind-bugs
Author
Source
getsentry/skills/skills/find-bugs @ a582c51
License
Apache-2.0 · Copyright 2025 Functional Software, Inc. dba Sentry

About this skill

What it does

The skill reviews the commits on the current branch and reports bugs, security holes and quality problems without touching the code. It reads the whole git diff <default>...HEAD, file by file if the output is cut off. For each changed file it first maps the attack surface — user input, database queries, auth checks, session state, external calls, cryptography — and then runs an eleven-item checklist: injection, XSS, authentication, authorization and IDOR, CSRF, race conditions, sessions, cryptography, information disclosure, DoS, business logic.

A suspected issue is checked before it is reported: is it handled elsewhere in the change, does a test cover it, does the surrounding code confirm it. Before the verdict the agent lists the files it read in full, the outcome of every checklist item and what it could not verify. Findings are ordered security, bugs, quality, each with file and line, a severity from Critical to Low, the problem, the evidence, a fix and, where relevant, an OWASP or RFC reference. Style is skipped, and an empty report is a valid result.

The folder holds only SKILL.md and the licence.

When to use it, and when not

Use it on a feature branch before a PR, when you want a security-first pass with a record of what was checked.

It sees committed work only. It needs an authenticated gh to find the default branch. It fixes nothing — the instructions end with "I'll decide what to address" — and has nothing to say about design or naming.

How to run it

The install command below puts the folder in place. The agent picks the skill up by its description when asked to find bugs or review the branch; to call it yourself:

  • Claude Code: /find-bugs, or ask for the skill by name.
  • Codex: $find-bugs.
  • Cursor: type / in the Agent chat and pick find-bugs.

Example: /find-bugs Check this branch before I open the PR, especially the new export endpoint.

How it differs from similar skills

Code review, Sentry practices from the same pack is the general reviewer: design, tests, tone of comments, when to approve. Security review, Sentry goes deeper into vulnerabilities, with per-topic references, data-flow tracing and only high-confidence findings; find-bugs is a lighter checklist that also catches ordinary bugs. PR review from our catalog puts correctness first and wants a concrete failure scenario for every bug; find-bugs starts from security and goes item by item. Security review from our catalog covers security only: it traces each untrusted input the change touches to a dangerous sink and reports only findings with an attacker, an input and an outcome. Self-review before PR is the author's pass before opening the PR: it also reads uncommitted and untracked files and checks debug leftovers, scope and migrations.

Install

Run one command — it saves SKILL.md and the files it uses into your agent's skills folder. Claude Code and Codex pick up a new skill without a restart; if it does not show up, restart the agent.

Claude Code — macOS, Linux
curl -fsSL --create-dirs -o ~/.claude/skills/find-bugs/SKILL.md https://anymodel.org/en/skills/sentry/find-bugs/SKILL.md -o ~/.claude/skills/find-bugs/LICENSE https://anymodel.org/en/skills/sentry/find-bugs/LICENSE
Codex, Cursor — macOS, Linux
curl -fsSL --create-dirs -o ~/.agents/skills/find-bugs/SKILL.md https://anymodel.org/en/skills/sentry/find-bugs/SKILL.md -o ~/.agents/skills/find-bugs/LICENSE https://anymodel.org/en/skills/sentry/find-bugs/LICENSE
Claude Code — Windows PowerShell
foreach ($f in 'SKILL.md','LICENSE') { $p = Join-Path "$HOME\.claude\skills\find-bugs" $f; New-Item -ItemType Directory -Force (Split-Path $p) | Out-Null; Invoke-WebRequest "https://anymodel.org/en/skills/sentry/find-bugs/$f" -UseBasicParsing -OutFile $p }
Codex, Cursor — Windows PowerShell
foreach ($f in 'SKILL.md','LICENSE') { $p = Join-Path "$HOME\.agents\skills\find-bugs" $f; New-Item -ItemType Directory -Force (Split-Path $p) | Out-Null; Invoke-WebRequest "https://anymodel.org/en/skills/sentry/find-bugs/$f" -UseBasicParsing -OutFile $p }

Any other agent: save the file into its skills folder, or give it the link to the file: https://anymodel.org/en/skills/sentry/find-bugs/SKILL.md

SKILL.md

Raw

Find Bugs

Review changes on this branch for bugs, security vulnerabilities, and code quality issues.

Phase 1: Complete Input Gathering

  1. Get the FULL diff: git diff $(gh repo view --json defaultBranchRef --jq '.defaultBranchRef.name')...HEAD
  2. If output is truncated, read each changed file individually until you have seen every changed line
  3. List all files modified in this branch before proceeding

Phase 2: Attack Surface Mapping

For each changed file, identify and list:

  • All user inputs (request params, headers, body, URL components)
  • All database queries
  • All authentication/authorization checks
  • All session/state operations
  • All external calls
  • All cryptographic operations

Phase 3: Security Checklist (check EVERY item for EVERY file)

  • Injection: SQL, command, template, header injection
  • XSS: All outputs in templates properly escaped?
  • Authentication: Auth checks on all protected operations?
  • Authorization/IDOR: Access control verified, not just auth?
  • CSRF: State-changing operations protected?
  • Race conditions: TOCTOU in any read-then-write patterns?
  • Session: Fixation, expiration, secure flags?
  • Cryptography: Secure random, proper algorithms, no secrets in logs?
  • Information disclosure: Error messages, logs, timing attacks?
  • DoS: Unbounded operations, missing rate limits, resource exhaustion?
  • Business logic: Edge cases, state machine violations, numeric overflow?

Phase 4: Verification

For each potential issue:

  • Check if it's already handled elsewhere in the changed code
  • Search for existing tests covering the scenario
  • Read surrounding context to verify the issue is real

Phase 5: Pre-Conclusion Audit

Before finalizing, you MUST:

  1. List every file you reviewed and confirm you read it completely
  2. List every checklist item and note whether you found issues or confirmed it's clean
  3. List any areas you could NOT fully verify and why
  4. Only then provide your final findings

Output Format

Prioritize: security vulnerabilities > bugs > code quality

Skip: stylistic/formatting issues

For each issue:

  • File:Line - Brief description
  • Severity: Critical/High/Medium/Low
  • Problem: What's wrong
  • Evidence: Why this is real (not already fixed, no existing test, etc.)
  • Fix: Concrete suggestion
  • References: OWASP, RFCs, or other standards if applicable

If you find nothing significant, say so - don't invent issues.

Do not make changes - just report findings. I'll decide what to address.

Connect through AnyModel API

This skill runs on whatever model your agent uses. Point Claude Code, Codex or Cursor at AnyModel to run it on Claude, GPT, Gemini and more with one key — pay per token, no subscription.

More from the pack Sentry skills

AGENTS.md and CLAUDE.md writer

Writes or trims a repository's AGENTS.md to under 60 lines of commands, conventions and pointers to existing docs, checks every path, and makes CLAUDE.md a symlink to it. Use when a repo needs agent instructions or its current file has grown long or stale.

Claude Code settings audit

Detects a repository's stack and proposes a Claude Code settings.json allow list of read-only commands for the tools it actually uses, plus docs domains and Sentry or Linear MCP entries. Use when setting up Claude Code permissions or auditing existing ones.

Code review, Sentry practices

Reviews a change by Sentry's guidelines: runtime errors, performance and N+1 queries, side effects, compatibility, security, design and tests, with a polite tone and approval once only minor issues remain. Use when reviewing a pull request or branch.

Code simplifier

Simplifies recently changed code without changing behaviour: less nesting, no nested ternaries, clearer names, no redundant abstractions, while following CLAUDE.md conventions. Use when code works but reads heavier than it should and needs a cleanup pass.

Conventional commit messages

Commits in Sentry's Conventional Commits style: a feature branch instead of main, a typed capitalised subject up to 70 characters, Fixes or Refs footers, no personal data. Use when asked to commit changes or draft a commit message.

Django access control review

Audits Django and DRF code for IDOR and broken access control by learning the app's authorization model and tracing each endpoint from ID to query, reporting only confirmed gaps with enforcing fixes. Use when reviewing views, viewsets or tenant isolation.

GitHub Actions security review

Audits GitHub Actions workflows for attacks an outsider without write access can run: pwn requests, expression injection, comment commands, token theft, poisoned agent configs, unpinned actions. Use when reviewing CI security or changing workflows.

Iterate a PR until CI is green

Drives an open PR to green: fixes failing CI and high and medium review comments, verifies locally, commits, pushes and repeats, stopping at human approval or draft gates. Use when a PR is red or has review feedback to work through.

PR title and description writer

Writes or refreshes a PR title in Sentry's conventional format and a short reviewer-facing description without template headings or test logs, then opens a draft or updates the PR. Use when opening a PR or after commits change its scope.

Prompt optimizer

Writes, repairs or ports system and agent prompts against a small eval set, comparing candidate rewrites on the same cases and checking the winner on held-out ones. Use when a prompt is unreliable, moves to another model family or needs evals.

Secret leaks through serialization

Finds secrets that leak when a credential field on a dataclass, pydantic model or JS object meets code that logs or traces whole objects, searching the whole repository for the other half. Use when a change adds such a field or a wholesale sink.

SECURITY_MODEL.md for review tools

Writes and maintains SECURITY_MODEL.md, telling security review tools a repository's exposure, invariants, reportable finding classes and owner-confirmed exclusions, with a script that flags stale references. Use when preparing a repo for automated review.

Agent skill security scanner

Audits an agent skill before installation: a static scan for prompt injection, hidden Unicode, secrets, risky scripts and structural traps, then a review of intent and permissions ending in a verdict. Use when a skill comes from an outside source.

Skill writer by the Agent Skills spec

Creates and improves agent skills by Sentry's workflow: sources with provenance, the simplest execution shape, SPEC.md and SOURCES.md, precision passes after each change and a structural validator. Use when building a skill that a team will maintain.

Security review, Sentry

Reviews a file, diff or component for exploitable vulnerabilities with OWASP-based references, researches the codebase before flagging and reports only findings reached by attacker-controlled input. Use when a change needs a low-noise security review.

Django performance review

Reviews Django and DRF code for N+1 queries, unbounded querysets, missing indexes and write loops, validating table size and hot paths before reporting. Use when a Django view or endpoint is slow or a change touches large tables.