agentmods.dev

bash-tool-path

A setup guide for adding folders to the PATH used by Claude Code's Bash tool. It covers cases where a command works in your terminal but cannot be found by Claude Code.

In plain words
What is it for?
Use it to configure command-line tools from folders such as go/bin, cargo, asdf shims, or custom tool directories for Claude Code.
Why use it?
It explains why common PATH settings can replace the existing PATH or be treated as literal text, causing commands or required tools to disappear.

Skill for Claude CodeCodex

23 3d ago B scan 104 tokens original MIT
View the source file drn/dots
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/drn/dots/bash-tool-path
Any agent
npx skills add drn/dots --skill bash-tool-path
Clone the repo
git clone --depth 1 https://github.com/drn/dots

Made for: Claude Code, Codex.

Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,140 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00104 $0.01140
Opus 5 $0.00052 $0.00570
Sonnet 5 $0.00021 $0.00228
Haiku 4.5 $0.00010 $0.00114

Measured 2d ago against content hash 5281971a933c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

bash-tool-path 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 2d 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.

- Existing SessionStart hooks (user): !`grep -n SessionStart ~/.claude/settings.json 2>/dev/null | head -10`
agents/skills/bash-tool-path/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context

  • Worked example hook: ~/.dots/agents/hooks/session-start-path.sh
  • Existing SessionStart hooks (user): !grep -n SessionStart ~/.claude/settings.json 2>/dev/null | head -10
  • env.PATH in user settings (a footgun if present): !grep -n '"PATH"' ~/.claude/settings.json 2>/dev/null | head -5

When to use this skill

Use this when a command that works in an interactive terminal fails with "command not found" inside Claude Code's Bash tool, or when the user wants to add a directory (a go/bin, cargo, asdf shim, or custom tool dir) to the PATH that Claude Code's Bash tool sees.

Why the obvious fixes do not work

Three footguns make this harder than it looks. State them plainly so nobody re-discovers them by hand.

  1. settings.json env values are set literally. Claude Code does not expand $VAR or ${VAR} in them. So "PATH": "${PATH}:/x/bin" sets PATH to that literal, broken string, not to the inherited PATH plus a directory.

  2. env.PATH replaces the inherited PATH wholesale. It cannot append, and replacing it drops the directories Claude Code already needs (for example plugin bin dirs). So env.PATH is the wrong tool for adding a dir.

  3. The Bash tool sources ~/.zshrc (or ~/.bashrc/~/.profile) at session start only to capture aliases, functions, and shell options. PATH export lines in ~/.zshrc or ~/.zshenv are not captured. Claude Code builds the Bash tool PATH from the process that launched it (often a daemon), not from your interactive shell, so daemon-launched sessions can lack go/bin and similar dirs even though they resolve fine in your terminal.

The supported fix: a SessionStart hook that writes to CLAUDE_ENV_FILE

Claude Code sources the file named by $CLAUDE_ENV_FILE before every Bash command. Because the file is sourced, $PATH expands at source time, so you can prepend a directory and preserve the inherited PATH. Populate that file from a SessionStart hook. $CLAUDE_ENV_FILE is available to the SessionStart, Setup, CwdChanged, and FileChanged hooks.

Read the full file on GitHub · 93 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. 2d ago First seen · 93 lines · 104 tokens per session scan B 5281971a933c

Subscribe to this mod's changes

bash-tool-path is a skill published in the GitHub repository drn/dots (23 stars, last pushed 3d ago), licensed MIT. It adds 104 tokens to every session and 1,140 once invoked, about $0.0005 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 2026-08-30.

Languages
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

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens