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 skills add b33eep/claude-code-setup --skill standards-shellgit clone --depth 1 https://github.com/b33eep/claude-code-setupWrote 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/b33eep/claude-code-setup/standards-shell)<a href="https://agentmods.dev/skills/b33eep/claude-code-setup/standards-shell"><img src="https://agentmods.dev/badge/skills/b33eep/claude-code-setup/standards-shell/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/b33eep/claude-code-setup/standards-shell"><img src="https://agentmods.dev/badge/skills/b33eep/claude-code-setup/standards-shell.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 | $0.00033 | $0.02406 |
| Opus 5.5 | $0.00013 | $0.00962 |
| Sonnet 5.5 | $0.00007 | $0.00481 |
| Haiku 4.5 | $0.00003 | $0.00241 |
Grade B, and why
standards-shell scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
echo "This script must be run as root" >&2 Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
retry 3 5 curl -f "https://api.example.com/health" How it starts
The opening of the file, as written. The whole thing — 397 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shell/Bash Coding Standards
Core Principles
- Simplicity: Simple, understandable scripts
- Readability: Readability over cleverness
- Maintainability: Scripts that are easy to maintain
- Testability: Scripts that are easy to test
- DRY: Don't Repeat Yourself - but don't overdo it
- Defensiveness: Fail early, fail loudly
General Rules
- Defensive Header: Always use
set -euo pipefail - Quote Variables: Always quote variables
"$var" - Descriptive Names: Meaningful names for variables and functions
- Minimal Changes: Only change relevant code parts
- No Over-Engineering: No unnecessary complexity
- ShellCheck Clean: All scripts must pass ShellCheck
Naming Conventions
| Element | Convention | Example |
|---|---|---|
| Variables | snake_case | user_name, file_count |
| Functions | snake_case | get_user_by_id, validate_input |
| Constants | UPPER_SNAKE_CASE | MAX_RETRIES, DEFAULT_TIMEOUT |
| Files | kebab-case or snake_case | deploy-app.sh, run_tests.sh |
| Environment Vars | UPPER_SNAKE_CASE | API_URL, DATABASE_HOST |
Script Template
#!/bin/bash
set -euo pipefail
readonly SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
readonly SCRIPT_NAME="$(basename "${BASH_SOURCE[0]}")"
# Cleanup on exit
cleanup() {
rm -f "$SCRIPT_DIR"/*.tmp 2>/dev/null || true
}
trap cleanup EXIT
# Error handler
error_handler() {
echo "Error on line $1" >&2
exit 1
}
trap 'error_handler $LINENO' ERR
main() {
# Script logic here
echo "Running $SCRIPT_NAME"
}
main "$@"
Defensive Scripting
# REQUIRED: Always start with this
set -euo pipefail
# -e: Exit on error
# -u: Error on undefined variables
# -o pipefail: Pipe fails if any command fails
# RECOMMENDED: Safer IFS
IFS=$'\n\t'
# REQUIRED: Quote all variables
echo "$var" # Good
echo $var # Bad - word splitting
# REQUIRED: Use [[ ]] for conditionals (Bash)
if [[ -f "$file" ]]; then # Good
if [ -f "$file" ]; then # POSIX only
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.
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.
- 1mo ago First seen · 397 lines · 33 tokens per session scan B 7dc5d1b469f9
standards-shell is a skill published in the GitHub repository b33eep/claude-code-setup (57 stars, last pushed 11d ago), licensed MIT. It adds 33 tokens to every session and 2,406 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 2 findings (asks for root, 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
scaffold-cli
Scaffolds a TypeScript CLI and npm package with the house toolchain, dual tsdown outputs, CLI contracts, changesets, and publishing templates. Use when asked to "scaffold a CLI" or "start an npm package".
relay-deploy
Set up a complete deployment configuration — Dockerfile, deployment manifest, environment config, and rollback procedure. Use when asked about "deployment setup", "how do I deploy this", "deployment strategy", or "rollback plan".
relay-pipeline
Build a full CI/CD pipeline from scratch. Use when asked to "set up CI/CD", "create pipeline", or "automate deploys".
touch-release
Set up mobile release pipeline — Fastlane, code signing, CI, beta distribution, versioning. Use when asked about "app store setup", "release pipeline", "fastlane", "beta distribution", or "signing".
pypi-ops
Publish Python packages to PyPI via OIDC Trusted Publishing (PEP 740 attestations, gh-action-pypi-publish) instead of stored tokens. Use for: invalid-publisher errors, pending-publisher 404s, uv publish/twine, TestPyPI, environment approval gates, and rotating/auditing publish tokens.
pipeline-digest
Daily release-pipeline digest with a change gate — reports which plugins are pending release, whether main's CI is green, and which branches went stale, and notifies the operator only when that state actually moved since the last run. Use when the operator asks "what moved in the pipeline", "anything to ship"…