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 saeedkolivand/ai-job-hunter-app --skill extension-standardsgit clone --depth 1 https://github.com/saeedkolivand/ai-job-hunter-appWrote 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/saeedkolivand/ai-job-hunter-app/extension-standards)<a href="https://agentmods.dev/skills/saeedkolivand/ai-job-hunter-app/extension-standards"><img src="https://agentmods.dev/badge/skills/saeedkolivand/ai-job-hunter-app/extension-standards/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/saeedkolivand/ai-job-hunter-app/extension-standards"><img src="https://agentmods.dev/badge/skills/saeedkolivand/ai-job-hunter-app/extension-standards.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 | $0.00075 | $0.01847 |
| Opus 5 | $0.00037 | $0.00924 |
| Sonnet 5 | $0.00015 | $0.00369 |
| Haiku 4.5 | $0.00007 | $0.00185 |
Grade A, and why
extension-standards 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 9d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Extension + bridge standards
Standards for the browser extension and the desktop⇄extension bridge. Load with author-contract (authors) / token-efficiency (reviewers).
Architecture & paths
- Extension (
apps/extension/**) — MV3, published on Chrome Web Store and Firefox AMO. Content scripts on supported job boards → import the user-selected posting into the desktop app. - Bridge — the extension reaches the desktop app over a loopback-only WebSocket (
127.0.0.1, a fixed port range) and Chrome Native Messaging (the native host relays frames verbatim). Server:apps/desktop/src-tauri/src/extension_bridge/**+commands/extension_bridge.rs. - Wire contract —
packages/shared/src/ipc/extension-protocol-constants.ts(envelope +EXTENSION_MESSAGE_TYPES), its zod schemaextension-protocol.ts, and the Rustmsgconstants in the bridge. A Rust↔TS parity test pins the message-type strings together.
Auth model (the security boundary)
- The per-frame 256-bit pairing token (loopback only) is what authenticates. The origin allowlist (Chrome id / Firefox UUID-shape / native-host sentinel) is defense-in-depth only.
- A connection is authorized/connected ONLY after a frame passes the token check — never on the WS handshake alone. On open the extension sends
{ type: "auth", token, reqId, payload: null }; the desktop replies animport.resultwith noerror(= authorized) or{ error: "unauthorized" }and closes the socket. A wrong token is never reported as connected. (This is the fix for the "any token looks authorized" bug — don't regress it.) - Never echo/confirm the token back; never log it. Token file is owner-only (
0o600) on unix.
Protocol lockstep (don't let the two sides drift)
A new message type/field is added in the same change to: the TS EXTENSION_MESSAGE_TYPES constant, the TS zod ExtensionMessageTypeSchema, and the Rust msg module. The envelope shape (type / token / reqId / payload) stays identical on both sides. The parity + uniqueness tests must stay green.
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.
- 9d ago First seen · 67 lines · 75 tokens per session scan A 05713d4b0955
extension-standards is a skill published in the GitHub repository saeedkolivand/ai-job-hunter-app (55 stars, last pushed yesterday), licensed Apache-2.0. It adds 75 tokens to every session and 1,847 once invoked, about $0.0004 per session on Opus 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 2026-09-03.
Other skills, from other repositories
anarlog
Query Anarlog meetings, notes, summaries, transcripts, participants, action items, and recurring history. Use when a user asks about their Anarlog meeting data or needs meeting context for another task.
tauri-pilot
Inspect, interact with, and test a running Tauri v2 app via CLI. Communicates over Unix socket using JSON-RPC 2.0. Use when testing UI, automating interactions, or debugging a Tauri app.
webapp-testing
Web application testing principles. E2E, Playwright, deep audit strategies.
run-in-altai
Keep Colab and Jupyter work inside the ALTAI app. When the user or another agent asks to run something on Colab or in a Jupyter notebook, use ALTAI's native webview tab (Colab) and notebook tab (Jupyter) instead of sending the user to a browser or a separate jupyter process.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-optimizer
Optimize what selected Next.js client navigations include before the click under Partial Prefetching. Use after Cache Components and Partial Prefetching are adopted when the user wants selected URL-specific UI to be instant, wants reusable content to wait for navigation, or needs to choose between default, viewport…