agentmods.dev

permissions

permissions is a command for coding agents from punt-labs/prfaq. It costs 16 tokens per session (775 once invoked), scanned B, original, MIT.

A project-level permission command for the prfaq plugin. It adds, checks, or removes rules in the project’s .claude/settings.json file, which controls approval prompts for that project.

In plain words
What is it for?
Use it to inspect current rules, grant the plugin permission to compile, edit, and search, or revoke those permissions.
Why use it?
It can reduce repeated approval requests while keeping the permissions visible and shared through the project repository.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the prfaq-dev plugin — 1 skill, 14 commands, 8 agents, 1 hook shipped together

not rated 25 4d ago B scan 16 tokens original MIT
View the source file punt-labs/prfaq
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 commands/punt-labs/prfaq/permissions
Clone the repo
git clone --depth 1 https://github.com/punt-labs/prfaq

Or install prfaq-dev, the plugin that ships this one along with the rest of its 1 skill, 14 commands, 8 agents, 1 hook.

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/punt-labs/prfaq/permissions.svg)](https://agentmods.dev/commands/punt-labs/prfaq/permissions)
Your own site
<a href="https://agentmods.dev/commands/punt-labs/prfaq/permissions"><img src="https://agentmods.dev/badge/commands/punt-labs/prfaq/permissions.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 775 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 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 $0.00016 $0.00775
Opus 5 $0.00008 $0.00387
Sonnet 5 $0.00003 $0.00155
Haiku 4.5 $0.00002 $0.00077

Measured 5d ago against content hash 147911aa0786, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

permissions scanned grade B with 2 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 5d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

global `~/.claude/settings.json`.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Deliberately excluded: `Bash(curl *)` and every `Bash(rm *)` form. Sending
plugin/commands/permissions.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Configure prfaq Permissions for This Project

Write prfaq's permission rules into this project's .claude/settings.json so the plugin's commands stop asking for approval on every compile, edit, and search. The rules apply to this project only — prfaq never writes to the global ~/.claude/settings.json.

Steps

  1. Pick the mode. Read $ARGUMENTS:

    • check (or status) — report which rules are present, change nothing
    • remove (or revoke, off) — take the rules back out
    • anything else, including empty — add the rules

  2. Confirm before writing. For the add and remove modes, tell the user which file will change (.claude/settings.json in the current project) and that the file is normally committed, so the change is visible to everyone working in the repo. Ask before proceeding. Skip this for check.

  3. Run the script.

    bash ${CLAUDE_PLUGIN_ROOT}/scripts/prfaq_permissions.sh --add

    Substitute --check or --remove for the other modes. The script operates on the current working directory and is idempotent — running it twice adds nothing the second time and leaves the file byte-identical.

  4. Report the result. Relay the script's output. When rules were added, tell the user two things:

    • Claude Code watches settings files, so the rules apply without a restart. Tell the user to restart only if they do not seem to have taken.
    • .claude/settings.json is checked into the repo, so committing it shares the permissions with the team. To keep them to themselves, they can move the block to .claude/settings.local.json, which is gitignored.

  5. If jq is missing. The script requires jq. When it reports jq missing, tell the user to install it (brew install jq on macOS, apt install jq on Linux) and offer to add the rules by hand instead — read the rule list out of ${CLAUDE_PLUGIN_ROOT}/scripts/prfaq_permissions.sh and write them into .claude/settings.json under permissions.allow.

Read the full file on GitHub · 63 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. 5d ago First seen · 63 lines · 16 tokens per session scan B 147911aa0786

Subscribe to this mod's changes

permissions is a command published in the GitHub repository punt-labs/prfaq (25 stars, last pushed 4d ago), licensed MIT. It adds 16 tokens to every session and 775 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

LaTeXSecuritybetaclaude-code-pluginpdf-generationproduct-discovery
Related

Other commands, from other repositories

oracle-dev

Generate property-based test harness using Lean 4 model as oracle.

punt-labs/z-spec · 12 tokens

refine-dev

Verify code refines Z specification via abstraction function and commutativity checks.

punt-labs/z-spec · 14 tokens

refine

Verify code refines Z specification via abstraction function and commutativity checks.

punt-labs/z-spec · 14 tokens

contracts-dev

Generate runtime contracts (preconditions, postconditions, invariants) from a Z specification.

punt-labs/z-spec · 17 tokens

code2model-dev

Create a Z specification for stateful entities in a system.

punt-labs/z-spec · 11 tokens

partition-dev

Derive test cases from Z specification using TTF testing tactics.

punt-labs/z-spec · 12 tokens