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 scaffold-zig-cligit 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/scaffold-zig-cli)<a href="https://agentmods.dev/skills/cboone/agent-harness-plugins/scaffold-zig-cli"><img src="https://agentmods.dev/badge/skills/cboone/agent-harness-plugins/scaffold-zig-cli/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/scaffold-zig-cli"><img src="https://agentmods.dev/badge/skills/cboone/agent-harness-plugins/scaffold-zig-cli.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 | $0.09494 |
| Opus 5.5 | $0.00019 | $0.03798 |
| Sonnet 5.5 | $0.00010 | $0.01899 |
| Haiku 4.5 | $0.00005 | $0.00949 |
Grade A, and why
scaffold-zig-cli 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 3d 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 — 540 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scaffold Zig CLI
Generate the full boilerplate for a new Zig CLI project.
Workflow
1. Gather Project Information
If the user provided a project name in their request, use it as the project name and skip asking for it. Still ask for the remaining parameters unless already provided in the user's initial request.
Ask the user for these parameters:
- Project name -- kebab-case, used as the binary name and directory name (e.g.,
my-tool) - Short description -- one sentence, used in the README
Validate the project name before using it anywhere. It becomes a directory name and a binary name, and step 3 passes it to mkdir and cd, so it must match [a-z0-9]+(-[a-z0-9]+)*: lowercase alphanumeric segments joined by single hyphens, nothing else. Reject anything else and ask again rather than repairing it.
That pattern is doing real work, not tidiness. A name beginning with a hyphen, -tool for instance, reads as options to mkdir -p and cd instead of as a path. A name containing / scaffolds into a different directory than the one reported. . and .. escape the target entirely. A name with whitespace or a shell metacharacter splits into several arguments. Quote the name wherever it reaches a command as well, so the pattern is the guarantee rather than the only defence.
Reject one more set the pattern lets through: the Windows reserved device names, which are con, prn, aux, nul, com1 through com9, and lpt1 through lpt9. The ranges start at 1, not 0: com0 and lpt0 are ordinary names and Microsoft's naming rules do not list them. Windows reserves the rest regardless of the extension, so con cannot be a directory, and con.exe and con.txt cannot be written or extracted either. The release workflow cross-compiles a Windows target and packages PROJECT-NAME.exe into a zip, so a project named con produces an archive nobody on Windows can unpack. Match them case-insensitively against the whole name; a name that merely contains one, like con-tool, is fine.
What ships with it
12 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.
- references/build-zig-zon.md 3.2 KB
- references/build-zig.md 5.2 KB
- references/ci-workflow.md 3.4 KB
- references/editorconfig.md 1.3 KB
- references/gitignore.md 1.5 KB
- references/license.md 1.6 KB
- references/main-zig.md 7.0 KB
- references/makefile.md 4.4 KB
- references/readme.md 2.3 KB
- references/release-workflow.md 2.5 KB
- references/root-zig.md 2.2 KB
- references/typos.md 2.1 KB
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.
- 3d ago Changed 0e0a3ce4a2b8
- 26d ago Changed · -7 lines · -107 tokens per session 5750914c4475
- 1mo ago First seen · 547 lines · 155 tokens per session scan A b0fb3db82de0
scaffold-zig-cli is a skill published in the GitHub repository cboone/agent-harness-plugins (2 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 9,494 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 2026-09-15.
Other skills, from other repositories
skillshare-app-release
A release workflow for shipping the skillshare desktop application on macOS, Windows, and Linux. It coordinates the release pull request, automated builds, GitHub release, updater feed, and Homebrew package.
land-and-deploy
Merge PR, wait for CI, verify deploy, run canary. The complete landing pipeline.
ci-all
Full CI pipeline: run local tests, type check, push branch, and return the pipeline URL. The only command you need before opening a PR.
ci-pipeline
Push current branch and return the pipeline tracking URL (GitLab or GitHub Actions).
ci-status
Show current pipeline status for the active branch (GitLab CI or GitHub Actions).
devops
CI/CD, container orchestration, cloud architecture, monitoring, infrastructure security, and platform automation skills. Docker, Kubernetes, Terraform, GitHub Actions. Triggers on: CI/CD, Docker, Kubernetes, Terraform, deploy, monitoring, infra, GitOps, observability, SRE.