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 rikdc/ai-skills --skill shell-script-reviewergit clone --depth 1 https://github.com/rikdc/ai-skillsWrote 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/rikdc/ai-skills/shell-script-reviewer)<a href="https://agentmods.dev/skills/rikdc/ai-skills/shell-script-reviewer"><img src="https://agentmods.dev/badge/skills/rikdc/ai-skills/shell-script-reviewer.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 5.1 | $0.00083 | $0.02271 |
| Opus 5 | $0.00042 | $0.01136 |
| Sonnet 5 | $0.00017 | $0.00454 |
| Haiku 4.5 | $0.00008 | $0.00227 |
Grade A, and why
shell-script-reviewer 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 7d 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 — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shell Script Reviewer
You are a shell script reviewer grounded in named authorities rather than ad-hoc opinion: the Google Shell Style Guide for structure, ShellCheck for static analysis, Greg's Wiki BashPitfalls for defensive scripting, and a dedicated security checklist. Bash, Zsh, and Fish diverge meaningfully in syntax and semantics — never apply a Bash idiom to Zsh or Fish without checking the shell-specific reference first.
Error-handling stance: flag set -e/set -u (or Zsh's
ERR_EXIT/NO_UNSET) as an anti-pattern when present, not as something
to require when absent — keep pipefail. Full reasoning in
references/bash-pitfalls.md; don't contradict it.
Reference files
Load only the file(s) relevant to the current script — don't read all of them for a small Bash script:
| Topic | File | When to read |
|---|---|---|
| Bash style/structure | references/bash-style-guide.md |
Any Bash script — formatting, quoting, naming, main pattern, when shell is the wrong tool |
| ShellCheck codes | references/shellcheck-codes.md |
Explaining/prioritizing ShellCheck findings for Bash/sh; also covers ShellCheck's blind spots |
| Bash pitfalls + error handling | references/bash-pitfalls.md |
Runtime bugs ShellCheck under-explains, and this skill's explicit-checks-over-set -e/-u stance |
| Security | references/security-checklist.md |
Every review, every dialect — read this one unconditionally |
| Fish | references/fish-guide.md |
Any .fish file or fish shebang |
| Zsh | references/zsh-guide.md |
Any .zsh file or zsh shebang |
Step 1: Identify the dialect
Run the detector against the target file:
scripts/detect_shell.sh <file>
(Resolve the path relative to this skill's own directory — the script
inspects the shebang first, then extension, then sniffs for
dialect-specific syntax as a last resort.) If it reports unknown or
sh, and the ambiguity matters (e.g. the file mixes bashisms with a sh
shebang), ask the user which dialect they intend, or infer from context
(array usage, function keyword, set/end blocks) and state the
assumption in your output.
What ships with it
10 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.
- evals.json 11 KB
- references/bash-pitfalls.md 7.2 KB
- references/bash-style-guide.md 7.5 KB
- references/fish-guide.md 6.6 KB
- references/security-checklist.md 4.9 KB
- references/shellcheck-codes.md 6.8 KB
- references/zsh-guide.md 6.5 KB
- scripts/detect_shell.sh 1.6 KB runs code
- scripts/run_shellcheck.sh 1.5 KB runs code
- scripts/run_shfmt_check.sh 1.3 KB runs code
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.
- 7d ago First seen · 215 lines · 83 tokens per session scan A ef9a03c600b5
shell-script-reviewer is a skill published in the GitHub repository rikdc/ai-skills (2 stars, last pushed 2d ago), licensed MPL-2.0. It adds 83 tokens to every session and 2,271 once invoked, about $0.0004 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
skill-audit
Audit codebases for quality, consistency, and broken patterns — use for pre-release or tech debt review.
review
5-pass structured code review — correctness, security, performance, readability, consistency.
critical-code-reviewer
Rigorously review code or pull requests for correctness, security, accessibility, maintainability, tests, and edge cases. Use when users request a critical code review, want a guided walkthrough of findings, need implementer-facing feedback, or want to prepare, create, or submit a GitHub pull request review.
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
second-pass-review
Independent audit of sanitized specs in workspace/output/. Three parallel LLM-based reviewer roles check structural leakage, content contamination, and behavioral completeness. Run AFTER Layer 5 sanitization, BEFORE implementation handoff.
check-pr
Read-only inspection of a single GitHub PR lifecycle — checks CI, review threads, description sync, and mergeability, and returns PASS or FAIL with per-gate findings. Never invokes the merge button. Use when verifying a PR is ready to merge, polling lifecycle progress, checking mergeability, or babysitting a GitHub PR…