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 zacharygcook/agent-skills --skill write-public-readmegit clone --depth 1 https://github.com/zacharygcook/agent-skillsWrote 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/zacharygcook/agent-skills/write-public-readme)<a href="https://agentmods.dev/skills/zacharygcook/agent-skills/write-public-readme"><img src="https://agentmods.dev/badge/skills/zacharygcook/agent-skills/write-public-readme/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/zacharygcook/agent-skills/write-public-readme"><img src="https://agentmods.dev/badge/skills/zacharygcook/agent-skills/write-public-readme.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 | $0.00056 | $0.00718 |
| Opus 5.5 | $0.00022 | $0.00287 |
| Sonnet 5.5 | $0.00011 | $0.00144 |
| Haiku 4.5 | $0.00006 | $0.00072 |
Grade A, and why
write-public-readme 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write Public README
Treat the README as the product's front door. Optimize for a capable stranger deciding whether to trust, install, and use the project—not for maintainers who already know its internals.
Build the story in reader order
- Inspect the repository, current README, license, package metadata, real commands, and screenshots.
- Identify the audience, primary outcome, maturity, and shortest verified path to first value.
- Lead with the project name, one concrete sentence, and a compact mental model or screenshot only when it materially improves understanding.
- Put installation and the human quick start before architecture, implementation details, or exhaustive reference material.
- Explain the distinctive workflows and benefits with evidence from the repository.
- End with automation/reference commands, deeper documentation, contribution guidance, license, and credits as applicable.
Make installation feel obvious
- Show the smallest supported path that actually works in a clean repository.
- Prefer one command per line and commands that fit a normal mobile-width GitHub code block.
- Do not expose package-layout details, redundant selectors, forced confirmation flags, interpreter spelling, manual file copies, or lifecycle glue when the product can automate them.
- Do not make humans read the automation interface to get started. Put fully explicit flags and machine-oriented variants in a small section near the end.
- If the honest command is ugly, improve the installer or CLI instead of cosmetically explaining it.
- Verify version behavior before adding
@latest, pins,-y, or similar ceremony.
Keep the README public-facing
- Write in plain, confident language. Remove internal history, private context, machine-specific paths, score-chasing rationale, apologies, and implementation archaeology.
- Prefer a few strong sections over a complete inventory. Link deeper docs rather than duplicating them.
- Use badges sparingly: build health, package/version, and license should communicate real trust.
- Use tables only for genuine comparison or exact mappings; avoid wide tables and horizontally scrolling command blocks.
- Keep examples realistic and copy/paste-ready. Separate shell commands from explanatory comments when comments make copying awkward.
- State access limitations, supported platforms, maturity, and destructive behavior plainly.
What ships with it
1 file 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.
- 1mo ago First seen · 70 lines · 56 tokens per session scan A e01e5311f4e4
write-public-readme is a skill published in the GitHub repository zacharygcook/agent-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 56 tokens to every session and 718 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 2026-08-31.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
cdf-anomalygen
Use when running the CDF AnomalyGen pipeline over a defect dataset — mask placement, fine-tuning, synthetic defect-image generation (SDG), evaluation, quality refinement, and pseudo-labeling — even when the user names only one stage.
deepstream-sop
Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary detection (GEBD) plus VLM classification. Trigger even if the…
hsb-ip-packetizer
Choose or explain HSB Sensor RX packetizer fields for HOLOLINKdef.svh. Do not use for full defs, validation, or runtime APB programming.
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
parabricks
Plan NVIDIA Parabricks pbrun commands, translate CPU options and check runtime readiness. Use for individual tools, including planning-only questions.