permissions

permissions is a command for Claude Code from Marcel-Bich/marcel-bich-claude-marketplace. It costs 24 tokens per session (1,609 once invoked), scanned A, original, MIT.

A command that creates or updates DOGMA-PERMISSIONS.md, a project file describing which actions Claude may perform automatically, must confirm first, or cannot perform.

In plain words
What is it for?
Use it to set rules for staging, committing, and pushing Git changes, and for deleting files.
Why use it?
It gives you a clear way to control risky actions instead of relying on unstated defaults. The settings cover Git operations and file changes such as deletion.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents; names the AskUserQuestion tool.

Part of the dogma plugin — 9 commands, 1 agent shipped together

Good fit Use it to set rules for staging, committing, and pushing Git changes, and for deleting files.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/marcel-bich/marcel-bich-claude-marketplace/permissions
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.

Clone the repo
git clone --depth 1 https://github.com/Marcel-Bich/marcel-bich-claude-marketplace

Made for: Claude Code.

Or install dogma, the plugin that ships this one along with the rest of its 9 commands, 1 agent.

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.

agentmods badge for permissions

README.md
[![agentmods](https://agentmods.dev/badge/commands/marcel-bich/marcel-bich-claude-marketplace/permissions/github.svg)](https://agentmods.dev/commands/marcel-bich/marcel-bich-claude-marketplace/permissions)
Your own site
<a href="https://agentmods.dev/commands/marcel-bich/marcel-bich-claude-marketplace/permissions"><img src="https://agentmods.dev/badge/commands/marcel-bich/marcel-bich-claude-marketplace/permissions/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.

agentmods 80×15 button for permissions

Your own site · 80×15
<a href="https://agentmods.dev/commands/marcel-bich/marcel-bich-claude-marketplace/permissions"><img src="https://agentmods.dev/badge/commands/marcel-bich/marcel-bich-claude-marketplace/permissions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,609 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00024 $0.01609
Opus 5 $0.00012 $0.00805
Sonnet 5 $0.00005 $0.00322
Haiku 4.5 $0.00002 $0.00161

Measured 11d ago against content hash 4af760c6fd98, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

permissions 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 11d 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.

plugins/dogma/commands/permissions.md · 275 lines

How it starts

The opening of the file, as written. The whole thing — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/dogma:permissions - Create Permissions File

Create or update DOGMA-PERMISSIONS.md to configure what Claude can do autonomously.

  1. Check if DOGMA-PERMISSIONS.md exists in project root
  2. If exists, show current permissions and ask if user wants to update
  3. If not exists, will create new file

Step 2: Git & File Permissions

Ask the user about each permission using AskUserQuestion. For each permission offer 3 choices:

  • auto [x]: Claude does it automatically
  • ask [?]: Claude asks for confirmation first
  • deny [ ]: Claude cannot do it (blocked)

Git Operations

git add

  • auto: Claude can stage files for commits
  • ask: Claude asks before staging
  • deny: User must run git add manually

git commit

  • auto: Claude can create commits autonomously
  • ask: Claude asks before committing
  • deny: User must create commits manually

git push

  • auto: Claude can push to remote repositories
  • ask: Claude asks before pushing (recommended)
  • deny: User must push manually

File Operations

Delete files

  • auto: Claude can run rm, unlink, git clean
  • ask: Claude prompts for confirmation before delete
  • deny: Deletion commands are logged to TO-DELETE.md for manual deletion

Step 3: Workflow Permissions

Ask about workflow automation settings.

3.1 Testing - When to run?

Ask: "When should tests be executed?"

Options (can select multiple):

  • before commit
  • before push
  • on tasklist completion

Default: [x] before commit, [x] before push, [x] on tasklist completion

3.2 Testing - What to test?

Ask: "What should be tested?"

Options:

  • relevant tests
  • silent-failure check - finds code that swallows errors (empty catch, ignored promises)

Default: [x] relevant tests, [x] silent-failure check

3.3 Review - When?

Read the full file on GitHub · 275 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. 11d ago First seen · 275 lines · 24 tokens per session scan A 4af760c6fd98

Subscribe to this mod's changes

permissions is a command published in the GitHub repository Marcel-Bich/marcel-bich-claude-marketplace (13 stars, last pushed 2d ago), licensed MIT. It adds 24 tokens to every session and 1,609 once invoked, about $0.0001 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 2026-08-30.