bash-approval-manager

A tool and guide for managing shell-command approval rules in the pi-bash-approval extension. It checks whitelist patterns, simulates whether commands are allowed, and can clean up duplicate or redundant rules with a backup.

In plain words
What is it for?
Use it to audit approval rules, test how a command matches them, identify regular-expression security problems, and remove duplicate entries safely.
Why use it?
It helps explain unexpected command blocks and find unsafe or overly broad approval patterns before they allow unwanted commands.

Skill for Claude CodeCodex

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 skills/testzugang/pi-plugins/bash-approval-manager
Any agent
npx skills add testzugang/pi-plugins --skill bash-approval-manager
Clone the repo
git clone --depth 1 https://github.com/testzugang/pi-plugins

Made for: Claude Code, Codex.

Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 604 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00063 $0.00604
Opus 5 $0.00032 $0.00302
Sonnet 5 $0.00013 $0.00121
Haiku 4.5 $0.00006 $0.00060

Measured 2d ago against content hash 19c7dd15b811, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bash-approval-manager 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 2d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/manager.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/bash-approval-manager/SKILL.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bash Approval Manager

Specialized assistant skill to audit, clean, and simulate whitelist patterns for the pi-bash-approval extension. Helps developers manage prompt fatigue, keep rules minimal, and prevent security vulnerabilities (such as command injection).

Capabilities

  1. Security & Quality Audit: Scan ~/.pi/agent/.bash-approval for:
    • Syntactically invalid regular expressions.
    • Security risks (e.g. unanchored rules, greedy .* wildcards).
    • Use of obsolete, vulnerable path pattern formulas (recommends the new injection-proof PATH_PATTERN).
    • Duplicate or redundant rule definitions.
  2. Automatic Cleanup: Removes exact duplicates and redundant literal rules (literals already covered by broader regex or glob rules) with automatic backup creation.
  3. Command Simulation: Explains step-by-step why a specific shell command is allowed or blocked, showing exactly which whitelist line matched which segment.

Usage

All features are provided by the bundled cross-platform Node utility script scripts/manager.mjs.

1. Run Security and Quality Audit

Scan your current whitelist for security risks, syntactical errors, duplicates, and redundant entries:

node skills/bash-approval-manager/scripts/manager.mjs audit

2. Auto-Clean Duplicates and Redundancies

Clean up your .bash-approval file automatically. This removes exact duplicates and redundant literal rules (and creates a safety backup of your original file!):

node skills/bash-approval-manager/scripts/manager.mjs clean

3. Simulate Matching and Splitting

Simulate how the bash-approval interceptor evaluates a given command. This shows segment-by-segment matches or blocks:

node skills/bash-approval-manager/scripts/manager.mjs simulate "git -C siblings/ai-agents-playground status"

Agent Workflows

When the user asks you to inspect, verify, debug, or clean their bash-approval rules, use the following steps:

  1. Identify the Goal: Determine if they want to find out why a command was blocked (use simulate), clean up rules (use clean), or check for security vulnerabilities (use audit).
  2. Run the Utility: Execute the corresponding subcommand via the bash tool.
  3. Synthesize Results: Present findings to the user. On auditing, explain what each warning means and give direct suggestions on how to improve the regex.

Read the full file on GitHub · 49 lines

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. 2d ago First seen · 49 lines · 63 tokens per session scan A 19c7dd15b811

Subscribe to this mod's changes

bash-approval-manager is a skill published in the GitHub repository testzugang/pi-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 604 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens