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.

SecurityPack: Sentry skills322 linesclaude-settings-audit
Author
Source
getsentry/skills/skills/claude-settings-audit @ a582c51
License
Apache-2.0 · Copyright 2025 Functional Software, Inc. dba Sentry

About this skill

What it does

The skill looks at a repository and proposes a permissions.allow list for Claude Code's .claude/settings.json, so read-only commands stop asking for approval. It detects the stack from indicator files (pyproject.toml, package.json and lock files, go.mod, Cargo.toml, Gemfile, pom.xml, Dockerfile, *.tf, monorepo configs), detects services (the Sentry SDK, Linear), reads any existing settings, then builds the list.

The list starts from a fixed baseline — ls, cat, find, head, tail, tree, read-only git subcommands, gh views of PRs, issues, runs and the repo, and gh api — plus version and listing commands only for tools the repo uses, such as poetry show or cargo tree. Other package managers, custom scripts, absolute paths and anything that installs, builds or writes stay out. Detected frameworks such as Django, Next.js or Rails get WebFetch permissions for their documentation sites.

For a Sentry project it adds Skill(sentry-skills:...) entries for Sentry's plugin and the Sentry docs domains, and suggests a .mcp.json entry for Sentry's hosted MCP server with your org and project slugs. If the repository uses Linear, it also suggests the Linear MCP server, which needs LINEAR_API_KEY. It never suggests a GitHub MCP server.

The answer is a table of what was detected, a complete settings.json to copy, MCP suggestions and merge notes. The folder holds only SKILL.md and the licence.

When to use it, and when not

Use it when setting up Claude Code on a new repository, or when approval prompts for harmless commands slow you down.

The output is Claude Code's settings format, so in Codex or Cursor it has little use. Read the list before merging: gh api:* also allows write calls to the GitHub API, and find:* allows find -delete.

How to run it

The install command below puts the folder in place. The agent picks the skill up by its description when you ask about Claude Code permissions; to call it yourself:

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

Example: /claude-settings-audit We already have .claude/settings.json. Suggest what to add for this pnpm monorepo and show the merged file.

How it differs from similar skills

Git guardrails for Claude Code works on the same settings file from the other side: a PreToolUse hook that blocks pushes and destructive git commands. This skill only widens what runs without asking, so the two fit together. Nothing else in the catalog builds a permission list.

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

SKILL.md

Raw

Claude Settings Audit

Analyze this repository and generate recommended Claude Code settings.json permissions for read-only commands.

Phase 1: Detect Tech Stack

Run these commands to detect the repository structure:

ls -la
find . -maxdepth 2 \( -name "*.toml" -o -name "*.json" -o -name "*.lock" -o -name "*.yaml" -o -name "*.yml" -o -name "Makefile" -o -name "Dockerfile" -o -name "*.tf" \) 2>/dev/null | head -50

Check for these indicator files:

Category Files to Check
Python pyproject.toml, setup.py, requirements.txt, Pipfile, poetry.lock, uv.lock
Node.js package.json, package-lock.json, yarn.lock, pnpm-lock.yaml
Go go.mod, go.sum
Rust Cargo.toml, Cargo.lock
Ruby Gemfile, Gemfile.lock
Java pom.xml, build.gradle, build.gradle.kts
Build Makefile, Dockerfile, docker-compose.yml
Infra *.tf files, kubernetes/, helm/
Monorepo lerna.json, nx.json, turbo.json, pnpm-workspace.yaml

Phase 2: Detect Services

Check for service integrations:

Service Detection
Sentry sentry-sdk in deps, @sentry/* packages, .sentryclirc, sentry.properties
Linear Linear config files, .linear/ directory

Read dependency files to identify frameworks:

  • package.json → check dependencies and devDependencies
  • pyproject.toml → check [project.dependencies] or [tool.poetry.dependencies]
  • Gemfile → check gem names
  • Cargo.toml → check [dependencies]

Phase 3: Check Existing Settings

cat .claude/settings.json 2>/dev/null || echo "No existing settings"

Phase 4: Generate Recommendations

Build the allow list by combining:

Baseline Commands (Always Include)

[
  "Bash(ls:*)",
  "Bash(pwd:*)",
  "Bash(find:*)",
  "Bash(file:*)",
  "Bash(stat:*)",
  "Bash(wc:*)",
  "Bash(head:*)",
  "Bash(tail:*)",
  "Bash(cat:*)",
  "Bash(tree:*)",
  "Bash(git status:*)",
  "Bash(git log:*)",
  "Bash(git diff:*)",
  "Bash(git show:*)",
  "Bash(git branch:*)",
  "Bash(git remote:*)",
  "Bash(git tag:*)",
  "Bash(git stash list:*)",
  "Bash(git rev-parse:*)",
  "Bash(gh pr view:*)",
  "Bash(gh pr list:*)",
  "Bash(gh pr checks:*)",
  "Bash(gh pr diff:*)",
  "Bash(gh issue view:*)",
  "Bash(gh issue list:*)",
  "Bash(gh run view:*)",
  "Bash(gh run list:*)",
  "Bash(gh run logs:*)",
  "Bash(gh repo view:*)",
  "Bash(gh api:*)"
]

Stack-Specific Commands

Only include commands for tools actually detected in the project.

Python (if any Python files or config detected)
If Detected Add These Commands
Any Python python --version, python3 --version
poetry.lock poetry show, poetry env info
uv.lock uv pip list, uv tree
Pipfile.lock pipenv graph
requirements.txt (no other lock) pip list, pip show, pip freeze
Node.js (if package.json detected)
If Detected Add These Commands
Any Node.js node --version
pnpm-lock.yaml pnpm list, pnpm why
yarn.lock yarn list, yarn info, yarn why
package-lock.json npm list, npm view, npm outdated
TypeScript (tsconfig.json) tsc --version
Other Languages
If Detected Add These Commands
go.mod go version, go list, go mod graph, go env
Cargo.toml rustc --version, cargo --version, cargo tree, cargo metadata
Gemfile ruby --version, bundle list, bundle show
pom.xml java --version, mvn --version, mvn dependency:tree
build.gradle java --version, gradle --version, gradle dependencies
Build Tools
If Detected Add These Commands
Dockerfile docker --version, docker ps, docker images
docker-compose.yml docker-compose ps, docker-compose config
*.tf files terraform --version, terraform providers, terraform state list
Makefile make --version, make -n

Skills (for Sentry Projects)

If this is a Sentry project (or sentry-skills plugin is installed), include:

[
  "Skill(sentry-skills:agents-md)",
  "Skill(sentry-skills:blog-writing-guide)",
  "Skill(sentry-skills:brand-guidelines)",
  "Skill(sentry-skills:browse-local-sentry)",
  "Skill(sentry-skills:claude-settings-audit)",
  "Skill(sentry-skills:code-review)",
  "Skill(sentry-skills:code-simplifier)",
  "Skill(sentry-skills:commit)",
  "Skill(sentry-skills:create-branch)",
  "Skill(sentry-skills:django-access-review)",
  "Skill(sentry-skills:django-perf-review)",
  "Skill(sentry-skills:doc-coauthoring)",
  "Skill(sentry-skills:document-api-endpoint)",
  "Skill(sentry-skills:find-bugs)",
  "Skill(sentry-skills:gh-review-requests)",
  "Skill(sentry-skills:gha-security-review)",
  "Skill(sentry-skills:iterate-pr)",
  "Skill(sentry-skills:pr-link-issue)",
  "Skill(sentry-skills:pr-screenshots)",
  "Skill(sentry-skills:pr-writer)",
  "Skill(sentry-skills:presentation-creator)",
  "Skill(sentry-skills:prompt-optimizer)",
  "Skill(sentry-skills:secret-serialization)",
  "Skill(sentry-skills:security-model)",
  "Skill(sentry-skills:security-review)",
  "Skill(sentry-skills:skill-scanner)",
  "Skill(sentry-skills:skill-writer)",
  "Skill(sentry-skills:sred-project-organizer)",
  "Skill(sentry-skills:sred-work-summary)",
  "Skill(sentry-skills:triage-frontend-issues)",
  "Skill(sentry-skills:typing-exclusion-worker)"
]

WebFetch Domains

Always Include (Sentry Projects)
[
  "WebFetch(domain:docs.sentry.io)",
  "WebFetch(domain:develop.sentry.dev)",
  "WebFetch(domain:docs.github.com)",
  "WebFetch(domain:cli.github.com)"
]
Framework-Specific
If Detected Add Domains
Django docs.djangoproject.com
Flask flask.palletsprojects.com
FastAPI fastapi.tiangolo.com
React react.dev
Next.js nextjs.org
Vue vuejs.org
Express expressjs.com
Rails guides.rubyonrails.org, api.rubyonrails.org
Go pkg.go.dev
Rust docs.rs, doc.rust-lang.org
Docker docs.docker.com
Kubernetes kubernetes.io
Terraform registry.terraform.io

MCP Server Suggestions

MCP servers are configured in .mcp.json (not settings.json). Check for existing config:

cat .mcp.json 2>/dev/null || echo "No existing .mcp.json"
Sentry MCP (if Sentry SDK detected)

Add to .mcp.json (replace {org-slug} and {project-slug} with your Sentry organization and project slugs):

{
  "mcpServers": {
    "sentry": {
      "type": "http",
      "url": "https://mcp.sentry.dev/mcp/{org-slug}/{project-slug}"
    }
  }
}
Linear MCP (if Linear usage detected)

Add to .mcp.json:

{
  "mcpServers": {
    "linear": {
      "command": "npx",
      "args": ["-y", "@linear/mcp-server"],
      "env": {
        "LINEAR_API_KEY": "${LINEAR_API_KEY}"
      }
    }
  }
}

Note: Never suggest GitHub MCP. Always use gh CLI commands for GitHub.

Output Format

Present your findings as:

  1. Summary Table - What was detected
  2. Recommended settings.json - Complete JSON ready to copy
  3. MCP Suggestions - If applicable
  4. Merge Instructions - If existing settings found

Example output structure:

## Detected Tech Stack

| Category        | Found          |
| --------------- | -------------- |
| Languages       | Python 3.x     |
| Package Manager | poetry         |
| Frameworks      | Django, Celery |
| Services        | Sentry         |
| Build Tools     | Docker, Make   |

## Recommended .claude/settings.json

\`\`\`json
{
"permissions": {
"allow": [
// ... grouped by category with comments
],
"deny": []
}
}
\`\`\`

## Recommended .mcp.json (if applicable)

If you use Sentry or Linear, add the MCP config to `.mcp.json`...

Important Rules

What to Include

  • Only READ-ONLY commands that cannot modify state
  • Only tools that are actually used by the project (detected via lock files)
  • Standard system commands (ls, cat, find, etc.)
  • The :* suffix allows any arguments to the base command

What to NEVER Include

  • Absolute paths - Never include user-specific paths like /home/user/scripts/foo or /Users/name/bin/bar
  • Custom scripts - Never include project scripts that may have side effects (e.g., ./scripts/deploy.sh)
  • Alternative package managers - If the project uses pnpm, do NOT include npm/yarn commands
  • Commands that modify state - No install, build, run, write, or delete commands

Package Manager Rules

Only include the package manager actually used by the project:

If Detected Include Do NOT Include
pnpm-lock.yaml pnpm commands npm, yarn
yarn.lock yarn commands npm, pnpm
package-lock.json npm commands yarn, pnpm
poetry.lock poetry commands pip (unless also has requirements.txt)
uv.lock uv commands pip, poetry
Pipfile.lock pipenv commands pip, poetry

If multiple lock files exist, include only the commands for each detected manager.

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.

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.

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.

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.