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 adbertram/cli-tools --skill chrome-webstoregit clone --depth 1 https://github.com/adbertram/cli-toolsWrote 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/adbertram/cli-tools/chrome-webstore)<a href="https://agentmods.dev/skills/adbertram/cli-tools/chrome-webstore"><img src="https://agentmods.dev/badge/skills/adbertram/cli-tools/chrome-webstore/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/adbertram/cli-tools/chrome-webstore"><img src="https://agentmods.dev/badge/skills/adbertram/cli-tools/chrome-webstore.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 | $0.00100 | $0.00943 |
| Opus 5.5 | $0.00040 | $0.00377 |
| Sonnet 5.5 | $0.00020 | $0.00189 |
| Haiku 4.5 | $0.00010 | $0.00094 |
Grade A, and why
chrome-webstore 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 today.
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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<quick_start>
- Identify whether the task is listing creation, listing review, field-spec lookup, or another Chrome Web Store request.
- Read
references/listing-spec.yamlbefore quoting any field limit, required flag, or asset dimension. - Route creation work to
workflows/create-listing.mdand review work toworkflows/review-listing.md. - Use
references/search-optimization.mdonly when copy or discoverability guidance is needed. - Use
references/official-docs.mdwhen the user challenges or asks to verify a spec. </quick_start>
<essential_principles>
How This Skill Works
Principle 1: Data-driven field specs
All character limits, asset dimensions, formats, and required/optional flags live in references/listing-spec.yaml. Read the YAML — never recite limits from memory. When Google updates the requirements, only the YAML changes.
Principle 2: Two listing surfaces, four dashboard tabs
A CWS submission has two deliverable groups: (1) listing content (text + images on the public store page) and (2) compliance metadata (privacy, distribution, test instructions). The dashboard splits these into four tabs — Store Listing, Privacy, Distribution, Test Instructions — all must be complete before "Submit for Review" is enabled.
Principle 3: Assets first, copy second
Image assets have hard pixel dimensions and a review pass of their own. Produce assets to spec before writing descriptions so copy can reference what's shown in screenshots.
Principle 4: Single purpose is the spine
Every field (title, summary, description, permissions justification, category) must reinforce one narrow purpose. Google rejects or delays extensions whose listing suggests multiple purposes. </essential_principles>
What ships with it
5 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.
- today First seen · 77 lines · 100 tokens per session scan A eb8f9052f105
chrome-webstore is a skill published in the GitHub repository adbertram/cli-tools (6 stars, last pushed today), licensed MIT. It adds 100 tokens to every session and 943 once invoked, about $0.0004 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 2026-11-07.
chrome-webstore compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| chrome-webstoreadbertram/cli-tools | Skill | 6 | today | MIT | A | 100 | Claude Code, Codex |
| pixiv-cli-prFlanChanXwO/pixiv-cli | Skill | 132 | yesterday | MIT | A | 57 | Codex |
| pixiv-cli-reviewFlanChanXwO/pixiv-cli | Skill | 132 | yesterday | MIT | A | 52 | Codex |
| code-review-pythonsoulcodex/agentic | Skill | 10 | 7d ago | MIT | A | 59 | Claude Code, Codex |
| aios-codemap-opsrexleimo/aios | Skill | 62 | yesterday | MIT | B | 60 | Claude Code, Codex |
| aios-codemap-opsrexleimo/aios | Skill | 62 | yesterday | MIT | B | 60 | Claude Code, Codex |
| agentic-preflightelanthus/agentic-preflight | Skill | 2 | 2d ago | Apache-2.0 | A | 67 | Claude Code, Codex |