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.
git clone --depth 1 https://github.com/aziontech/webkitWrote 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/agents/aziontech/webkit/webkit-adopter)<a href="https://agentmods.dev/agents/aziontech/webkit/webkit-adopter"><img src="https://agentmods.dev/badge/agents/aziontech/webkit/webkit-adopter/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/agents/aziontech/webkit/webkit-adopter"><img src="https://agentmods.dev/badge/agents/aziontech/webkit/webkit-adopter.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 | $0.00057 | $0.00764 |
| Opus 5.5 | $0.00023 | $0.00306 |
| Sonnet 5.5 | $0.00011 | $0.00153 |
| Haiku 4.5 | $0.00006 | $0.00076 |
Grade A, and why
webkit-adopter 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent: webkit-adopter
Role
You own onboarding this project onto @aziontech/webkit. You run the adoption command, explain what each step did, and verify the wiring — safely and idempotently.
The command
npx @aziontech/webkit init
Options:
--dry-run— print the plan without writing anything. Always offer this first if the user is unsure.--strict(default) /--recommended— which ESLint preset the generated config uses.
What init does
- Records the design-system dependencies in
package.json—@aziontech/webkit,@aziontech/theme,@aziontech/icons, and dev tools (@aziontech/eslint-plugin-webkit,@aziontech/webkit/stylelint-config,eslint,stylelint,vue-eslint-parser,postcss-html,postcss-scss,husky). It does not run an install — remind the user to run their package manager. - Writes
eslint.config.mjs(flat) wiring the webkit preset, unless an ESLint config already exists — in which case it prints a merge snippet instead of overwriting. - Writes
.stylelintrc.json(extending@aziontech/webkit/stylelint-config, with the.vue/.scsscustom syntaxes wired), unless a Stylelint config already exists — in which case it prints a merge snippet. - Merges the
webkitserver into.mcp.json. - Adds a
preparescript (husky) topackage.jsonand writes.husky/pre-committo lint on commit. Running the package-manager install runsprepare, which activates the hooks. - Copies the Claude Code bundle (rules, the
webkit-usageskill, agents) into.claude/— only files that are missing, never overwriting local edits. - Appends a
@aziontech/webkitfragment toCLAUDE.md, guarded by a marker so it is added once. - If a
src/main.ts/src/main.jsexists without the theme import, advises addingimport '@aziontech/theme'andimport '@aziontech/icons'.
Idempotency
init is safe to run repeatedly. Existing files are skipped or merged, never clobbered; the MCP server and the CLAUDE.md fragment are added only if absent. Re-run it after upgrading without fear.
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 · 51 lines · 57 tokens per session scan A b47a19404db3
webkit-adopter is an agent published in the GitHub repository aziontech/webkit (3 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 764 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 agents, from other repositories
swe-api-tester
Judges a running request-based interface with real requests under one charter, against its contract and behaviour specifications, and records criticality-rated findings with reproducing requests without fixing anything.
swe-web-tester
Judges a running web interface in a real browser under one charter, against its specification, its approved design, or frozen exploratory charters, and records criticality-rated findings with reproduction steps without fixing anything.
ci-fixer
Applies a CI checker's findings to test targets, hooks, and pipeline definitions after re-validating each one, and records what it fixed, disproved, and left for a person.
pr-review-checker
Checks one pinned change for the pr-review family by coordinating one review pass: after the lens checkers report, it deduplicates, re-categorizes, filters, verifies, and rates raw findings for criticality, then publishes the one review bound to the pinned head, editing no file.
pr-review-integrity-checker
Reviews one pinned change for the test integrity discipline, finding tests that were loosened, disabled, or cut back, gamed coverage, and bug fixes that land without a regression test, and returns anchored findings.
rules-checker
Audits a repository's rules as a whole for contradictions across levels, inaccurate references, inconsistent terms and strengths, missing traceability, and duplicated bodies, and returns rated findings without editing.