Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/skills/ruizrica/agent-pi/just-bash)<a href="https://agentmods.dev/skills/ruizrica/agent-pi/just-bash"><img src="https://agentmods.dev/badge/skills/ruizrica/agent-pi/just-bash/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.
<a href="https://agentmods.dev/skills/ruizrica/agent-pi/just-bash"><img src="https://agentmods.dev/badge/skills/ruizrica/agent-pi/just-bash.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00057 | $0.01761 |
| Opus 5 | $0.00028 | $0.00881 |
| Sonnet 5 | $0.00011 | $0.00352 |
| Haiku 4.5 | $0.00006 | $0.00176 |
Grade A, and why
just-bash scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **No network access** - cannot curl, wget, or make connections How it starts
The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Just Bash Skill
Overview
Use this skill when you need to:
- Run bash commands safely without modifying the real filesystem
- Process and transform data files (CSV, JSON, YAML, text)
- Test shell scripts in an isolated sandbox
- Run exploratory commands where mistakes can't cause damage
- Execute complex pipelines (grep, awk, sed, jq, xan, rg)
- Validate scripts before running them for real
When to use just-bash vs the regular Bash tool:
- just-bash: Exploratory work, data processing, script testing, untrusted input, bulk file operations where you want safety
- Regular Bash: git operations, npm/pip commands, running servers, anything needing network or real writes
Prerequisites
# Install globally
npm install -g just-bash
# Or use via npx (no install needed)
npx just-bash -c 'echo hello'
Core Usage
Run Inline Commands
# Simple command
just-bash -c 'ls -la'
# Multi-line script
just-bash -c '
for f in *.ts; do
echo "$(wc -l < "$f") $f"
done | sort -rn | head -10
'
Run Script Files
just-bash ./scripts/analyze.sh
Pipe Scripts from Stdin
echo 'find . -name "*.ts" | head -5' | just-bash
Key Options
--root <path> # Mount a specific directory (default: cwd)
--cwd <path> # Set working directory inside sandbox
--allow-write # Enable in-memory writes (writes don't touch real FS)
--python # Enable python3 commands
--json # Output as JSON: {"stdout", "stderr", "exitCode"}
-e, --errexit # Exit on first error
Security Model
- Read-only by default - reads real files via OverlayFS, blocks writes
- No network access - cannot curl, wget, or make connections
- No escape - sandboxed to the root directory
- In-memory writes - with
--allow-write, writes go to memory only, not disk - Real filesystem is mounted at
/home/user/project
Available Commands (75+)
Text Processing
awk sed grep egrep fgrep rg cut tr sort uniq wc head tail tac rev nl fold expand unexpand column comm join paste split strings
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.
- 9d ago First seen · 198 lines · 57 tokens per session scan A b7d37954e803
just-bash is a skill published in the GitHub repository ruizrica/agent-pi (266 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 1,761 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…