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 tetherto/wdk-agent-skills --skill wdk-review-jsdocsgit clone --depth 1 https://github.com/tetherto/wdk-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/tetherto/wdk-agent-skills/wdk-review-jsdocs)<a href="https://agentmods.dev/skills/tetherto/wdk-agent-skills/wdk-review-jsdocs"><img src="https://agentmods.dev/badge/skills/tetherto/wdk-agent-skills/wdk-review-jsdocs/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/tetherto/wdk-agent-skills/wdk-review-jsdocs"><img src="https://agentmods.dev/badge/skills/tetherto/wdk-agent-skills/wdk-review-jsdocs.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 | $0.00038 | $0.06392 |
| Opus 5.5 | $0.00015 | $0.02557 |
| Sonnet 5.5 | $0.00008 | $0.01278 |
| Haiku 4.5 | $0.00004 | $0.00639 |
Grade A, and why
wdk-review-jsdocs 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 — 683 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WDK JSDoc & Type Annotation Review
Review the source files at the provided path (or the current project's src/ directory if none given). Apply all rules below.
For each violation found, report:
- Rule violated (e.g., R1, R2, TD1, etc.)
- File and line
- The offending code
- Suggested fix with corrected code
Group findings by file. After all files are reviewed, provide a summary with total violation counts per rule.
WDK Types & JSDoc Standards
You are reviewing source files for a WDK (Wallet Development Kit) module. Apply the rules below to identify JSDoc and type-annotation violations and suggest fixes.
The rules are repository-agnostic. No WDK module is a "golden reference" — apply every rule to every module equally. If existing code conflicts with a rule, the code is the candidate for change, not the rule.
JSDoc Format Rules
R1. Every JSDoc block must start with a plain-text description before any tags
Tags like @param, @returns, @type must not appear before the description.
Violation:
/**
* @param {Provider} provider - An ethers provider.
* @returns {Promise<string>} The address.
*/
Correct:
/**
* Returns the wallet address from the given provider.
*
* @param {Provider} provider - An ethers provider.
* @returns {Promise<string>} The address.
*/
R2. Use {Object} (capitalized) in @typedef kind-markers and @template constraints, not {object}
/** @typedef {object} GetBalanceResult */ // wrong — use Object as the kind-marker
/** @typedef {Object} GetBalanceResult */ // correct
/** @template {object} TSchema */ // wrong
/** @template {Object} TSchema */ // correct — consistent with all other WDK modules
This applies only to @typedef kind-markers and @template constraints. Using {Object} as a value type in @param, @property, @returns, or @type is forbidden — see R13 (the single-use options-bag pattern in R25 is the one exception).
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 · 683 lines · 38 tokens per session scan A b58a5c4fed5e
wdk-review-jsdocs is a skill published in the GitHub repository tetherto/wdk-agent-skills (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 38 tokens to every session and 6,392 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 2026-09-04.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…