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.
npx agentmods add skills/cboone/agent-harness-plugins/check-zsh-scriptsnpx skills add cboone/agent-harness-plugins --skill check-zsh-scriptsgit clone --depth 1 https://github.com/cboone/agent-harness-pluginsWrote 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/cboone/agent-harness-plugins/check-zsh-scripts)<a href="https://agentmods.dev/skills/cboone/agent-harness-plugins/check-zsh-scripts"><img src="https://agentmods.dev/badge/skills/cboone/agent-harness-plugins/check-zsh-scripts.svg" alt="Measured on agentmods" 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 | $0.00151 | $0.01994 |
| Opus 5 | $0.00076 | $0.00997 |
| Sonnet 5 | $0.00030 | $0.00399 |
| Haiku 4.5 | $0.00015 | $0.00199 |
Grade A, and why
check-zsh-scripts 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 4d 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.
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.
How it starts
The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Check Zsh Scripts
Check and evaluate zsh scripts using multiple complementary static analysis, syntax checking, and formatting tools.
Tool Overview
| Order | Tool | Purpose | Zsh Support | Auto-Fix |
|---|---|---|---|---|
| 1 | zsh -n |
Syntax check (parse without execute) | Native | No |
| 2 | zcompile |
Compile to wordcode | Native | No |
| 3 | shellcheck --shell=bash |
Static analysis | Limited | No |
| 4 | checkbashisms |
Identify bash-specific constructs | Indirect | No |
| 5 | shellharden --check |
Safer syntax suggestions | Limited | Suggest |
| 6 | zsh -c 'setopt ...; source' |
Variable scope warnings | Native | No |
| 7 | shfmt -ln zsh |
Shell formatter | Experimental | Yes |
Workflow
1. Identify Files to Check
Scan the project for zsh files using Glob:
**/*.zsh**/.zshrc,**/.zshenv,**/.zprofile,**/.zlogin,**/.zlogout**/zshrc,**/zshenv,**/zprofile,**/zlogin,**/zlogout
For other shell scripts, use Read to check shebangs for #!/usr/bin/env zsh or #!/bin/zsh.
If the user specified particular files, use those instead of scanning.
If no zsh files are found, report this and stop.
2. Check Tool Availability
For each tool, verify installation:
command -v zsh
command -v shellcheck
command -v checkbashisms
command -v shellharden
command -v shfmt
zcompile is a zsh builtin and does not need a separate check.
Present a table of available vs. missing tools. For missing tools, show the install command from the tool's reference file and continue with available tools.
Minimum requirement: zsh must be available (pre-installed on macOS).
What ships with it
7 files 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.
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.
- 4d ago First seen · 213 lines · 151 tokens per session scan A 6d386a1ecad7
check-zsh-scripts is a skill published in the GitHub repository cboone/agent-harness-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 151 tokens to every session and 1,994 once invoked, about $0.0008 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.
Other skills, from other repositories
feature-spec
Creates a complete product feature specification with acceptance criteria, scope, dependencies, and risks. Delegates to the Prometeo (PM) agent.
implement-feature
Implements a feature from its specification. Reads the spec, designs architecture, writes code and tests. Delegates to the Forja (Dev) agent.
best-practices
Searchable knowledge base of 152+ programming best practices across 30+ languages and frameworks. BM25-powered search over curated resources from industry leaders (Google, Airbnb, Uber, Mozilla, Shopify, OWASP).
aidd-dev:00:sdlc
Pure orchestrator for the full AIDD development flow. Use when a human (or Gardener) needs to take a free-form request from idea to shipped code, end-to-end. Coordinates spec generation, planning, implementation, and review by composing other skills and agents. Holds no business logic of its own — every step is…
software-code-refactoring
Improve production code quality while preserving all existing test behavior. Commonly used for the Refactor phase of TDD red-green-refactor, but applicable to any codebase with tests. Use when production code works but needs cleanup — reducing duplication, improving naming, simplifying complexity, aligning with…
02-user-stories
Produces or refines ordered User Stories from an Epic, Product Brief, PRD, or bounded request. Use when the user wants to slice, write, assess, order, or persist Stories. Not for Epics or implementation.