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 wyattowalsh/agents --skill shell-scriptergit clone --depth 1 https://github.com/wyattowalsh/agentsWrote 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/wyattowalsh/agents/shell-scripter)<a href="https://agentmods.dev/skills/wyattowalsh/agents/shell-scripter"><img src="https://agentmods.dev/badge/skills/wyattowalsh/agents/shell-scripter/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/wyattowalsh/agents/shell-scripter"><img src="https://agentmods.dev/badge/skills/wyattowalsh/agents/shell-scripter.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 | $0.00048 | $0.01968 |
| Opus 5.5 | $0.00019 | $0.00787 |
| Sonnet 5.5 | $0.00010 | $0.00394 |
| Haiku 4.5 | $0.00005 | $0.00197 |
Grade A, and why
shell-scripter 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 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.
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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shell Scripter
Generate, review, convert, and lint shell scripts. Makefile and justfile generation. References ShellCheck rule IDs with explanations but does NOT run ShellCheck.
Scope: Shell scripts (bash, zsh, fish, sh/POSIX), Makefiles, justfiles. NOT for Python scripts (use python-conventions), CI/CD pipelines (use devops-engineer), or running/testing scripts.
Dispatch
| $ARGUMENTS | Mode |
|---|---|
create <description> |
Generate a shell script from natural language |
review <script or path> |
Audit for pitfalls, reference ShellCheck rules |
convert <script or path> <target> |
Dialect conversion (bash/zsh/fish) |
posix <script or path> |
POSIX compliance check at pattern level |
makefile <tasks> |
Generate a Makefile from task descriptions |
justfile <tasks> |
Generate a justfile from task descriptions |
| Natural language about shell scripting | Auto-detect mode from intent |
| Empty | Show mode menu with examples |
Auto-Detection Heuristic
- Path to
.sh/.bash/.zsh/.fishfile + modification verb (review, check, fix, audit, lint) -> review - Path to
.shfile + "to zsh/fish/bash" -> convert - Path to
.shfile + "posix" or "portable" -> posix - "makefile" or "make targets" in input -> makefile
- "justfile" or "just recipes" in input -> justfile
- Describes desired script behavior -> create
- Ambiguous -> ask which mode
Mode: Create
Generate a shell script from a natural language description.
Generation Process
- Determine target dialect (default: bash)
- Run
uv run python scripts/dialect-converter.py --list-features <dialect>to confirm available features - Write the script with:
- Proper shebang (env-based like
env bash, not hardcoded interpreter paths) set -euo pipefailfor bash (equivalent for other dialects)- Meaningful variable names, quoted expansions
- Error handling for external commands
- Usage function if script accepts arguments
- Proper shebang (env-based like
What ships with it
21 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/convert-dialect.json 496 B
- evals/create-script.json 603 B
- evals/evals.json 2.1 KB
- evals/implicit-trigger.json 468 B
- evals/negative-control.json 340 B
- evals/review-script.json 563 B
- references/common-pitfalls.md 4.3 KB
- references/dialect-differences.md 4.3 KB
- references/makefile-justfile.md 5.0 KB
- references/posix-compatibility.md 3.7 KB
- references/shellcheck-rules.md 5.5 KB
- scripts/asset_toolkit/__init__.py 303 B runs code
- scripts/asset_toolkit/_shared.py 5.6 KB runs code
- scripts/asset_toolkit/common.py 3.0 KB runs code
- scripts/asset_toolkit/package.py 43 KB runs code
- scripts/asset_toolkit/validate_evals.py 11 KB runs code
- scripts/asset_toolkit/validate_hooks.py 13 KB runs code
- scripts/asset_toolkit/validate_skill.py 3.6 KB runs code
- scripts/check.py 2.2 KB runs code
- scripts/dialect-converter.py 8.9 KB runs code
- scripts/script-analyzer.py 8.7 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.
- 1mo ago First seen · 185 lines · 48 tokens per session scan A e476f91e6ad5
shell-scripter is a skill published in the GitHub repository wyattowalsh/agents (5 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 1,968 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…