safe-shell-script-author SKILL.md skillF
safe-shell-script-author from gsa-tts/agentic-coding-patterns is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add gsa-tts/agentic-coding-patterns/safe-shell-script-author@v1.0.0Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- F, 15 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- gsa-tts/agentic-coding-patterns
- Path
.agents/skills/safe-shell-script-author/SKILL.md- Versions recorded
- 4
- Latest version
- v1.0.0, committed Aug 20, 2026
- First version recorded
- Jul 2, 2026
- Size
- 10,769 bytes
- Repository stars
- 16
- License
- CC0-1.0
Draft safe Bash scripts to a clean-script standard (set -euo pipefail, mktemp + trap cleanup, quoted expansions, dry-run default, shellcheck/shfmt-clean) — never curl|sh, eval, or secret dumps; used when a task asks for a new shell script.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Skill: Safe Shell Script Author Draft a **new Bash script** from a stated intent, built to a **clean-script standard**: strict mode (`set -euo pipefail`), `mktemp` + `trap` cleanup, quoted expansions, a `--help` usage block, and a **dry-run default** that needs `--apply` to mutate anything. The output is a script plus a short rationale for each safety property. > **This skill DRAFTS scripts; it never executes them.** Every script it emits > defaults to dry-run and must be read and run by a human. It refuses to produce > `curl | sh`, `eval` on external data, or code that dumps secrets. Authoritative > secure-coding policy lives in the > [agentic-coding-playbook](https://github.com/GSA-TTS/agentic-coding-playbook); > this skill points there rather than restating it. ## When to Use - A task asks you to write a new Bash automation, cleanup, or setup script - You want a safe skeleton (strict mode, cleanup, dry-run) as a starting point - You need the "why" behind each safety choice for a review ## When NOT to Use - To **run** a script — this skill only drafts; a human executes - To review or repair an **existing** script (that is a separate review task) …
Read the whole file at its exact version.
How to install
mdr add gsa-tts/agentic-coding-patterns/safe-shell-script-author@sha256:da408f809141b628The line at the top of this page pins the label v1.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_xbtrahb6bw75qux4)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Jul 2, 2026 and Aug 20, 2026, about one every 16 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.0.0 latest | 2026-08-20 | ae5b0dd | 10,769 B | F | view · diff |
| v1.0.0 | 2026-07-28 | ea6ea67 | 10,763 B | F | view · diff |
| v1.0.0 | 2026-07-07 | 9620b72 | 10,467 B | F | view · diff |
| v1.0.0 | 2026-07-02 | c736287 | 10,282 B | F | view |
Audit of the latest version
- FAIL, critical: No zero-width or bidi control characters (matched: )
- fail: No curl or wget piped into a shell (matched: curl|sh)
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (10769 bytes)
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.
Source
gsa-tts/agentic-coding-patterns · 16 stars · license CC0-1.0 · pushed 2026-10-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_xbtrahb6bw75qux4 GET https://markdownregistry.com/api/v1/resolve?ref=gsa-tts/agentic-coding-patterns/safe-shell-script-author GET https://markdownregistry.com/api/v1/blob/da408f809141b6285429b3f39bf7bbde26742b550067ca9302e538957a130d05
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.