reset-permissions

reset-permissions is a skill for Claude Code from ivklgn/ai-kit. It costs 56 tokens per session (611 once invoked), scanned B, original, MIT.

A command for clearing saved Claude Code permissions from a project's local settings file. It can remove every allowed permission or keep read-only permissions while removing action permissions.

In plain words
What is it for?
It resets permissions in `.claude/settings.local.json`, either completely or selectively with the read-only option.
Why use it?
It helps clean up permissions that accumulated during earlier work and reduces the set of actions the coding agent is allowed to perform.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; reads .claude/ paths; mentions Claude Code.

Part of the ai-kit plugin — 22 skills, 15 commands, 30 agents, 1 MCP server shipped together

Good fit It resets permissions in .claude/settings.local.json, either completely or selectively with the read-only option.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ivklgn/ai-kit/reset-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.

Any agent
npx skills add ivklgn/ai-kit --skill reset-permissions
Clone the repo
git clone --depth 1 https://github.com/ivklgn/ai-kit

Made for: Claude Code.

Or install ai-kit, the plugin that ships this one along with the rest of its 22 skills, 15 commands, 30 agents, 1 MCP server.

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 reset-permissions

README.md
[![agentmods](https://agentmods.dev/badge/skills/ivklgn/ai-kit/reset-permissions/github.svg)](https://agentmods.dev/skills/ivklgn/ai-kit/reset-permissions)
Your own site
<a href="https://agentmods.dev/skills/ivklgn/ai-kit/reset-permissions"><img src="https://agentmods.dev/badge/skills/ivklgn/ai-kit/reset-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 reset-permissions

Your own site · 80×15
<a href="https://agentmods.dev/skills/ivklgn/ai-kit/reset-permissions"><img src="https://agentmods.dev/badge/skills/ivklgn/ai-kit/reset-permissions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 611 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00056 $0.00611
Opus 5 $0.00028 $0.00305
Sonnet 5 $0.00011 $0.00122
Haiku 4.5 $0.00006 $0.00061

Measured 7d ago against content hash d3014fab5db9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade B, and why

reset-permissions scanned grade B with 1 finding 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 7d 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.

cat .claude/settings.local.json
plugins/ai-kit/skills/reset-permissions/SKILL.md · 53 lines

What it actually says

Reset Permissions

Clear accumulated permissions.allow entries from .claude/settings.local.json in the current project.

Modes

  • No arguments — full reset, clear all permissions
  • --keep-read — remove only write/action permissions, keep read-only

Step 1: Read Current Settings

cat .claude/settings.local.json

If the file doesn't exist or has no permissions.allow entries, report that there are no permissions to reset and stop.

Step 2: Classify Permissions

For --keep-read mode, classify each permission in the allow array:

Read-only (KEEP):

  • WebFetch(*), WebSearch
  • Read(*), Glob(*), Grep(*)
  • Bash with read commands: find, ls, cat, head, tail, tree, diff, grep, rg, wc, file, stat, du, df, which, type, env, printenv, echo
  • Bash with git read commands: git status, git log, git diff, git show, git branch, git tag, git remote, git blame, git ls-files, git ls-tree, git describe, git rev-parse, git shortlog, git reflog, git stash list
  • Commands ending with --list, --help, --version

Write/action (REMOVE):

  • Everything else: Bash(mkdir:*), Bash(chmod:*), Bash(rm:*), Bash(git add:*), Bash(git commit:*), Bash(git push:*), Bash(git:*) (blanket git), Edit(*), Write(*), install/build scripts, etc.

Step 3: Apply Changes

Use the Edit tool to update .claude/settings.local.json:

  • Full reset: replace the allow array contents with []
  • --keep-read: replace the allow array with only the read-only entries

Preserve all other fields in the file (deny, enabledPlugins, etc.) unchanged.

Step 4: Report Results

Show the user:

  1. How many permissions were removed (list them with - prefix)
  2. For --keep-read: how many were kept (list them with + prefix)
  3. Confirm the file was updated
Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 7d ago First seen · 53 lines · 56 tokens per session scan B d3014fab5db9

Subscribe to this mod's changes

reset-permissions is a skill published in the GitHub repository ivklgn/ai-kit (12 stars, last pushed 7d ago), licensed MIT. It adds 56 tokens to every session and 611 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.

Related

Other skills, from other repositories

goal-delivery-completeness

Check that delivered work matches the user's goal. Use before final response, release, or handoff.

lubochka/xiigen-general-skills · 27 tokens

session-output-contract

Make session output useful, complete, and resumable. Use at handoff, final response, or long-running task summary.

lubochka/xiigen-general-skills · 29 tokens

stale-baseline-guard

Avoid acting on outdated context. Use after interruptions, long sessions, branch changes, or concurrent edits.

lubochka/xiigen-general-skills · 27 tokens

notion_synthesize

Synthesize durable ktx wiki pages and semantic-layer sources from staged Notion pages, databases, data-source rows, and clustered Notion evidence. Load when a WorkUnit contains Notion raw files or Notion evidence chunks.

Kaelio/ktx · 50 tokens

codex-skin-pack-installer

Install Codex themes and Codex skin packs with npx skills. Use this skill when a user wants Codex to find, download, validate, apply, switch, remix, or restore Codex desktop themes such as caishen-readable, caishen-lite, mythic-guardian-noir, global-founder-bright, export-night, or caishen-max. It stages verified…

hashgraph-online/awesome-codex-plugins · 125 tokens

find-journalists

Build, refine, dedupe, and enrich small fit-checked journalist lists for newsjack campaigns. Uses the newsjack CLI (preferred) or the medialyst MCP for news search and journalist enrichment, and falls back to a best-effort local mode with no verified contacts; the agent owns how returned data is organized.

elvisun/newsjack · 69 tokens