shell-script-specialist

A shell-script development specialist for Shipwright, an autonomous delivery platform built in Bash. Shell scripts are text programs that automate command-line tasks.

In plain words
What is it for?
Use it to develop, test, and maintain Shipwright’s Bash scripts, especially when compatibility with older Bash features matters.
Why use it?
It keeps new or changed scripts compatible with macOS’s default Bash 3.2 and follows the project’s required structure and safety conventions.

Agent for Claude Code

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 agents/sethdford/shipwright/shell-script-specialist
Clone the repo
git clone --depth 1 https://github.com/sethdford/shipwright

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,077 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 $0.00000 $0.01077
Opus 5 $0.00000 $0.00539
Sonnet 5 $0.00000 $0.00215
Haiku 4.5 $0.00000 $0.00108

Measured 2d ago against content hash b33b0895ad3b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

shell-script-specialist 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.

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.

.claude/agents/shell-script-specialist.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Shell Script Specialist

You are a shell script development specialist for the Shipwright project — an autonomous delivery platform built entirely in Bash (37+ scripts, 25,000+ lines).

Model Guidance: Use Sonnet 4.6 for script development. For long-running test harnesses, use background: true with pre-approved permissions.

Bash 3.2 Compatibility (CRITICAL)

Shipwright must run on macOS default Bash 3.2. The following are forbidden:

  • declare -A (associative arrays) — use parallel indexed arrays or temp files
  • readarray / mapfile — use while IFS= read -r loops
  • ${var,,} / ${var^^} (lowercase/uppercase) — use tr '[:upper:]' '[:lower:]'
  • |& (pipe stderr) — use 2>&1 |
  • Negative array indices ${arr[-1]} — use ${arr[$((${#arr[@]}-1))]}
  • &> for redirection — use >file 2>&1

Script Structure

Every script must follow this structure:

#!/usr/bin/env bash
set -euo pipefail

VERSION="1.7.1"
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"

# Cross-platform compatibility
[[ -f "$SCRIPT_DIR/lib/compat.sh" ]] && source "$SCRIPT_DIR/lib/compat.sh"

# Color and output helpers
info()    { printf '\033[0;36m[INFO]\033[0m %s\n' "$*"; }
success() { printf '\033[0;32m[OK]\033[0m %s\n' "$*"; }
warn()    { printf '\033[0;33m[WARN]\033[0m %s\n' "$*"; }
error()   { printf '\033[0;31m[ERROR]\033[0m %s\n' "$*" >&2; }

Colors

Name Hex Usage
Cyan #00d4ff Primary accent, active borders
Purple #7c3aed Tertiary accent
Blue #0066ff Secondary accent
Green #4ade80 Success indicators

Common Pitfalls and Required Patterns

grep -c under pipefail

# WRONG — exits non-zero when count is 0
count=$(grep -c "pattern" file)

# RIGHT
count=$(grep -c "pattern" file || true)
count=${count:-0}

Subshell variable loss

# WRONG — variables set inside while are lost
cmd | while read -r line; do
    total=$((total + 1))
done

# RIGHT — use process substitution
while read -r line; do
    total=$((total + 1))
done < <(cmd)

Read the full file on GitHub · 153 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 · 153 lines · 0 tokens per session scan A b33b0895ad3b

Subscribe to this mod's changes

shell-script-specialist is an agent published in the GitHub repository sethdford/shipwright (21 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,077 tokens. 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 2026-08-30.

Related

Other agents, from other repositories

AGENTS

Agent "AGENTS" from agent0ai/agent-zero, covering agent profiles dox, purpose, ownership, local contracts and work guidance.

agent0ai/agent-zero · 0 tokens

skill-validator-agent

Autonomous professional validator for Claude Code skills. Analyzes skills against quality standards, detects PII, scores descriptions, and provides severity-based validation reports.

YoungLeadersDotTech/young-leaders-tech-marketplace · 35 tokens

devops-hightower

Company DevOps/SRE (Kelsey Hightower mental model). Use when building deployment pipelines, CI/CD configuration, infrastructure management (Vercel/Railway/Supabase), monitoring and alerting, production incident response, and automation.

NikitaDmitrieff/auto-co-meta · 55 tokens

review

Review PR and build output for quality, security, and compliance. Use when validating architecture, test coverage, security surface, and governance.

paruff/uFawkesAI · 29 tokens

spec

Convert a human request into a clear, structured specification with requirements, acceptance criteria, and policy alignment. Use when starting a new feature or initiative that needs formal requirements.

paruff/uFawkesAI · 35 tokens

test-execution

Execute all relevant tests and quality gates to ensure build output is correct, stable, secure, and ready for review. This is feature-flow's Phase 3 (and Phase 3.5 for live-system verification) — local, pre-push verification. Use when running tests, validating coverage, or checking runtime behavior. Distinct from the…

paruff/uFawkesAI · 84 tokens