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 cboone/agent-harness-plugins --skill write-bash-scriptsgit clone --depth 1 https://github.com/cboone/agent-harness-pluginsWrote 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/cboone/agent-harness-plugins/write-bash-scripts)<a href="https://agentmods.dev/skills/cboone/agent-harness-plugins/write-bash-scripts"><img src="https://agentmods.dev/badge/skills/cboone/agent-harness-plugins/write-bash-scripts/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/cboone/agent-harness-plugins/write-bash-scripts"><img src="https://agentmods.dev/badge/skills/cboone/agent-harness-plugins/write-bash-scripts.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 | $0.00051 | $0.00566 |
| Opus 5.5 | $0.00020 | $0.00226 |
| Sonnet 5.5 | $0.00010 | $0.00113 |
| Haiku 4.5 | $0.00005 | $0.00057 |
Grade A, and why
write-bash-scripts scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bash Style Guide
Apply the Bash conventions from ./references/BASH.md when creating or editing Bash scripts.
Key Conventions
Read ./references/BASH.md for the complete guide. Summary:
Script Structure
- Shebang:
#!/usr/bin/env bash - Strict mode:
set -euo pipefail - Main function called at end:
main "$@"
Naming
- Functions:
snake_case - Local variables:
lower_case - Constants:
ALL_CAPSwithreadonly
Syntax
- Variable expansion:
${var}not$var, except the argument lists"$@"and"$*", which stay unbraced - Command substitution:
$(...)not backticks - Tests:
[[...]]not[...] - Function syntax:
function name() { }with both keyword and parentheses
Quoting
- Always quote variable expansions:
"${var}" - Always quote command substitutions:
"$(cmd)" - Use arrays for lists, not word splitting
- Guard an array that can be empty:
${array[@]+"${array[@]}"}
Local Variables
- Declare with
local - Separate declaration from command substitution to preserve exit codes
Bash 3.2 (macOS)
macOS ships bash 3.2 as /bin/bash, which is what #!/usr/bin/env bash finds on a stock Mac. Under set -u it exits on an empty "${@}" or "${array[@]}", and it has no associative arrays, readarray or mapfile, ${var,,} or ${var^^}, or namerefs. See "Bash 3.2 (macOS)" in ./references/BASH.md for replacements.
Pull Request Review
When reviewing a pull request, apply ./references/review-checklist.md: the rules of this guide that a reviewer can check in a diff, ranked as Important, Nits and Do not flag. The same checklist is installed into repositories for automated reviewers, so update it whenever a rule here changes.
Validation
Whenever possible, validate the script before finishing. Prefer using a project-specific validation script, if available. Common locations include declarations in package.json and scripts stored in bin/. If those aren't present, shellcheck is a commonly available linter for Bash scripts.
What ships with it
2 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.
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.
- 8d ago Changed · +1 lines · +19 tokens per session 976ba6e38a6d
- 25d ago Changed · +4 lines 720f9e8f16bb
- 26d ago Changed · -1 lines · -20 tokens per session b0533d82f376
- 1mo ago Changed · +5 lines 9e0498577498
- 1mo ago First seen · 50 lines · 52 tokens per session scan A 49d54f7a2999
write-bash-scripts is a skill published in the GitHub repository cboone/agent-harness-plugins (2 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 566 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
optimize-python-parallelism
Analyze and, when the task authorizes source optimization, refactor a concrete long-running Python entrypoint containing repeated independent work. Use for explicit Python speedup or parallelization requests and evidence-backed long-running entrypoints; skip ordinary Python edits, test execution alone, short scripts…
dotnet-reverse
A guide for analyzing compiled .NET and C# programs, including managed Windows executables and libraries. Reverse engineering means studying compiled software to understand how it works, and decompiling turns it back into readable approximate source code.
golang-error-handling
Idiomatic Golang error handling — creation, wrapping with %w, errors.Is/As, errors.Join, custom error types, sentinel errors, panic/recover, the single handling rule, structured logging with slog, HTTP request logging middleware, and samber/oops for production errors. Built to make logs usable at scale with log…
call-diagnostics
Analyze phone call observability data, detect problems, track them across calls, and recommend systematic repairs.
extending-personhog-test-harness
When and how to add scenarios, chaos events, and invariants to the personhog e2e test harness (rust/personhog-test-harness). Use after fixing a bug or regression in the personhog leader path (leader, router, writer, replica, coordination protocol) so the fix gets a permanent regression scenario; when adding a new…
python-lsp
Semantic Python code queries via a stdio LSP client driving pyright-langserver. Provides binding-resolved go-to-definition, find-references, hover types, type diagnostics, file symbol outlines, and project-wide symbol search — name resolution and type inference that tree-sitter and ripgrep cannot do. Use when you need…