Borrowing it
Nothing to install: this file belongs to sethdford/shipwright. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sethdford/shipwright/main/.claude/skills/port-bash-command/SKILL.mdgit clone --depth 1 https://github.com/sethdford/shipwrightWrote 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/sethdford/shipwright/port-bash-command)<a href="https://agentmods.dev/skills/sethdford/shipwright/port-bash-command"><img src="https://agentmods.dev/badge/skills/sethdford/shipwright/port-bash-command/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/sethdford/shipwright/port-bash-command"><img src="https://agentmods.dev/badge/skills/sethdford/shipwright/port-bash-command.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 | $0.00052 | $0.00772 |
| Opus 5.5 | $0.00021 | $0.00309 |
| Sonnet 5.5 | $0.00010 | $0.00154 |
| Haiku 4.5 | $0.00005 | $0.00077 |
Grade A, and why
port-bash-command 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 14d 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.
What it actually says
Never run a bash suite (scripts/*-test.sh) directly: many drive tmux and touch HOME and the
repo. Run suites only through the hermetic runners: bash scripts/sw-test-all.sh --pattern <name>
(against bash) or bun run parity (against TypeScript, in a sealed sandbox).
- Check the don't-port list in §7.5 of
docs/superpowers/specs/2026-10-13-shipwright-ts-migration-design.md. If the command (or the engine it belongs to) is listed there, stop and report it; do not port it. - Read the entry in
docs/plans/port/progress.json(command,aliases,script,context,parity). Leavestatusatbashfor now. - If
parityis null, writescripts/sw-<name>-test.shthat pins today's behavior (arguments, exit codes, output, files written) and record it in the entry. - Baseline against bash:
bash scripts/sw-test-all.sh --pattern sw-<name>-test.shmust pass before you change anything. - Implement in
src/contexts/<context>/: pure rules indomain/, the use case inapplication/, ports for any I/O, adapters insrc/adapters/. Writebun:testtests first (TDD). - Add the command in
src/cli/commands/(old names inaliases) and register it insrc/cli/commands/index.ts. - Set
statustoportingandgit addthe new files (the parity sandbox copies tracked files only). Runbun run parity. It copies the repo into a temporary sandbox with a privateHOME, tmux socket andTMPDIRand fail-closedclaude/ghshims, replaces the script of every entry atportingor later with a stub (exec bun <sandbox>/src/cli.ts <command> "$@"), runs the suite there, and fails if the real repo changed. A script shared with a command still atbashcannot be stubbed; parity reports that. Do not edit or replace the bash script: it stays as the reference implementation until the entry isbash-deleted(a separate change). - If an old assertion checks implementation (e.g. greps the script source), rewrite it to check behavior so it passes against both bash (step 3) and TypeScript (step 6), and say so in the commit message.
- When parity is green, set
statustoparity-green, then flip the router: inscripts/swreplace the entry'sexec "$SCRIPT_DIR/<script>" "$@"body withrun_ts <name> "$@", keeping every alias in the label, e.g.name|alias) run_ts name "$@" ;;.bun run port:checkrejects arun_tsroute whose entry is notparity-greenorbash-deleted. bun run docs:gen, thenbun run check(it includesport:checkandparity). Commit.
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.
- 14d ago First seen · 37 lines · 52 tokens per session scan A b5d8c1292b1b
port-bash-command is a skill published in the GitHub repository sethdford/shipwright (21 stars, last pushed today), licensed MIT. It adds 52 tokens to every session and 772 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 2026-10-15.
Other skills, from other repositories
typescript-test-writing
Use this skill when writing or modifying tests in the llxprt-code repository. Covers mandatory TDD, behavioral testing, bun:test conventions and file naming, mock hygiene (no mock theater), and what never to test. Distilled from dev-docs/RULES.md, which remains the source of truth.
agent-inspect
Local evidence debugger and trajectory-test toolkit for TypeScript AI agents. Use when capturing framework-faithful traces, asserting TraceContract/TraceFacts, packaging Evidence v2, or inspecting local runs over read-only MCP (gettracefacts).
typescript-eval
Test TypeScript code snippets before persisting as skills.
Unit Test Scaffold (TypeScript)
Generate TypeScript unit test skeletons (Jest/Vitest) from specifications.
programming-fsharp
Guides F# work under the F# standard: placing each new file in the compile order, reaching a red that fails on an assertion, choosing among option, result, and exception, and finding invariants worth a property-based test.
programming-javascript
Guides JavaScript work under the JavaScript standard: confirming the file is type-checked, typing through JSDoc, validating input the checker cannot see, and noticing floating promises and swallowed errors before handing off.