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/job-match-author)<a href="https://agentmods.dev/agents/saeedkolivand/ai-job-hunter-app/job-match-author"><img src="https://agentmods.dev/badge/agents/saeedkolivand/ai-job-hunter-app/job-match-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/job-match-author"><img src="https://agentmods.dev/badge/agents/saeedkolivand/ai-job-hunter-app/job-match-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 | $0.00051 | $0.00456 |
| Opus 5 | $0.00026 | $0.00228 |
| Sonnet 5 | $0.00010 | $0.00091 |
| Haiku 4.5 | $0.00005 | $0.00046 |
Grade A, and why
job-match-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 13d 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 ATS/job-match changes. First Read .claude/skills/author-contract/SKILL.md + .claude/skills/automation-standards/SKILL.md + .claude/skills/job-match-standards/SKILL.md (and docs/knowledge/matching-algorithm.md for the scoring kernel; subagents don't auto-load skills).
Primary paths
apps/desktop/src-tauri/src/commands/match_resume.rs, commands/cover_letter.rs, cover_letter/**, recommend/**, validate/**, and JD-content prompts. Owns ATS scoring/matching (ATS-safe formatting → pdf-docx-generator; provider infra → ai-provider-author).
Load-bearing rules
- Keep scoring deterministic and the keyword-coverage kernel the single source (
docs/knowledge/matching-algorithm.md) — don't fork a parallel scorer. - Never hardcode drift-prone weights/counts where the kernel owns them.
- ATS scoring / resume generation are not mocked in tests — use realistic fixtures.
Validate (cargo test on the touched crates) before done, write the handoff, hand the diff to job-match-expert.
Strict enforcement (enforced — raised bar)
Canonical rules → token-efficiency §Strict enforcement + author-contract (codegraph-first · mandatory validation gate · tests blocking · never approve your own work). Domain-specific HIGH examples:
- a forked/parallel scorer instead of the single keyword-coverage kernel; drift-prone hardcoded weights/counts the kernel owns; non-deterministic scoring.
- domain edge paths tests must cover: zero keyword overlap, empty/garbled JD, weight boundaries.
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.
- 13d ago First seen · 28 lines · 51 tokens per session scan A 6a587e07e9c6
job-match-author is an agent published in the GitHub repository saeedkolivand/ai-job-hunter-app (55 stars, last pushed yesterday), licensed Apache-2.0. It adds 51 tokens to every session and 456 once invoked, about $0.0003 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.
growth-engineer
Data Scientist & Growth Architect. Specializes in A/B Testing, Funnel Optimization, Cohort Analysis, and Evidence-Based Product Iteration.
orchestrator
Master Agent for Multi-Agent Coordination. Decomposes complex objectives into executable pipelines, invokes specialists, and synthesizes disparate outputs into a unified Truth.
project-planner
Technical Architect & Strategist. Specializes in task decomposition, system design, and the creation of executable blueprints. Converts "What" (PRD) into "How" (Atomic Tasks).
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.