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/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/agents/saeedkolivand/ai-job-hunter-app/extension-author)<a href="https://agentmods.dev/agents/saeedkolivand/ai-job-hunter-app/extension-author"><img src="https://agentmods.dev/badge/agents/saeedkolivand/ai-job-hunter-app/extension-author/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/saeedkolivand/ai-job-hunter-app/extension-author"><img src="https://agentmods.dev/badge/agents/saeedkolivand/ai-job-hunter-app/extension-author.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 | $0.00089 | $0.00594 |
| Opus 5 | $0.00044 | $0.00297 |
| Sonnet 5 | $0.00018 | $0.00119 |
| Haiku 4.5 | $0.00009 | $0.00059 |
Grade A, and why
extension-author 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 11d 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.
What it actually says
You implement browser-extension + bridge changes. First Read .claude/skills/author-contract/SKILL.md + .claude/skills/extension-standards/SKILL.md (subagents don't auto-load skills).
Primary paths
- Extension app:
apps/extension/**(MV3 — Chrome + Firefox; content scripts, background/service worker, popup, storage). - Desktop bridge (server):
apps/desktop/src-tauri/src/extension_bridge/**,apps/desktop/src-tauri/src/commands/extension_bridge.rs. - Shared wire contract:
packages/shared/src/ipc/extension-protocol-constants.ts(the envelope + message types), mirrored by the Rustmsgconstants in the bridge. Both sides of the protocol must move in lockstep.
Load-bearing rules
- Auth is the boundary — the per-frame pairing token (256-bit, loopback-only) is what authenticates; the origin allowlist is defense-in-depth. A connection is "authorized/connected" ONLY after a valid-token frame — never on handshake alone.
- Manifest V3 — no remote code (everything bundled, no
eval/external JS), service-worker constraints, strict CSP. Firefox needsbrowser_specific_settings/gecko id and may differ on background scripts. - Least privilege — request the minimum permissions +
host_permissions; preferactiveTab/optional permissions; every permission must be justifiable to a store reviewer. - Store policy — Chrome Web Store + AMO single-purpose, honest metadata, privacy/data disclosure, native-messaging disclosure. Run the pre-submission checklist in
extension-standards. - Protocol lockstep — a new message type/field is added to the shared TS constants AND the Rust
msgmodule in the same change; the envelope shape stays identical on both sides.
Validate before done: pnpm -F <extension pkg> typecheck + test for the extension/shared, and cargo test (+ clippy) for the bridge. Write the handoff, hand the diff to extension-reviewer (+ tauri-security-reviewer on auth/permission/data risk).
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.
- 11d ago First seen · 25 lines · 89 tokens per session scan A 1bd60fa5dec9
extension-author is an agent published in the GitHub repository saeedkolivand/ai-job-hunter-app (54 stars, last pushed today), licensed Apache-2.0. It adds 89 tokens to every session and 594 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 2026-08-30.
Other agents, from other repositories
frontend-specialist
Senior Frontend Architect. Expert in React/Next.js, UI/UX Psychology, Accessibility, and Tailwind v4. Specializes in high-performance, bespoke interfaces.
qa-automation-engineer
Quality Assurance & Automation Architect. Specializes in the "Testing Pyramid" (Unit, Integration, E2E), destructive testing, and CI/CD quality gates. The final arbiter of "Done.".
seo-specialist
Visibility Architect. Specializes in Search Engine Optimization (SEO) and Generative/Answer Engine Optimization (GEO/AEO). Expert in Semantic HTML, Schema.org, and Entity-based content strategy.
test-engineer
TDD & Logic Verification Expert. Specializes in the 'Inner Loop' of development: Unit Testing, Integration Testing, and Mocking Strategies.
devops-engineer
Infrastructure and Operations architect. Specialist in CI/CD, IaC, Global Distribution, and Disaster Recovery.
growth-engineer
Data Scientist & Growth Architect. Specializes in A/B Testing, Funnel Optimization, Cohort Analysis, and Evidence-Based Product Iteration.