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 job-match-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/job-match-standards)<a href="https://agentmods.dev/skills/saeedkolivand/ai-job-hunter-app/job-match-standards"><img src="https://agentmods.dev/badge/skills/saeedkolivand/ai-job-hunter-app/job-match-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/job-match-standards"><img src="https://agentmods.dev/badge/skills/saeedkolivand/ai-job-hunter-app/job-match-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 | $0.00088 | $0.01272 |
| Opus 5 | $0.00044 | $0.00636 |
| Sonnet 5 | $0.00018 | $0.00254 |
| Haiku 4.5 | $0.00009 | $0.00127 |
Grade A, and why
job-match-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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ATS scoring & job-match standards (reality, not myth)
External best-practices for ATS scoring, JD analysis, and resume↔job matching. Load with author-contract (job-match-author) / token-efficiency (job-match-expert). Pairs with docs/knowledge/matching-algorithm.md (the scoring kernel).
How real ATS work (verified 2026-06)
- No universal "ATS score." Each platform scores differently; a single portable percentage is marketing fiction. Present our number as a guidance estimate with evidence, never as the employer's verdict. https://www.hireflow.net/blog/workday-vs-greenhouse-vs-lever-which-parses-best
- Greenhouse — structured scorecards + Boolean over parsed fields; AI Talent Matching added Feb 2026. Lever — full-text relevance + Gem semantic JD understanding (not exact-keyword). Workday — weights job-title/seniority match heavily (mismatched title tanks the score). Taleo — strict literal keyword match. iCIMS — ML semantic match. Ashby — Boolean search; 0–100 Match Score + reason bullets only via AI add-ons.
- Recruiter Boolean/keyword search is still the dominant filter — candidates surface via search, not just auto-rank.
- AI/LLM screening — ~65% of US enterprise employers use AI-assisted screening (2025); LLM layers now score career-narrative fit + achievement quality. https://incruiter.com/blog/ai-in-recruitment-2026-trends-stats-what-works/
Matching best-practices (what our scorer should do)
- Extract JD requirements and classify hard (must-have/knockout) vs nice-to-have; treat knockout/screening questions as gating, not weighted.
- Normalize keywords + synonyms (title/skill aliases, seniority mapping) — helps both literal (Taleo) and semantic (iCIMS/Lever) parsers.
- Evidence-based scoring — credit skills backed by experience/context, not raw frequency; never reward keyword stuffing (semantic + AI-content detection penalize it). https://www.jobscan.co/blog/can-ats-detect-ai-resume/
- Explainable output — per-requirement match + reason bullets; be honest the number is our estimate.
- Invalidate derived caches on input change — when a posting's text changes (e.g. the full description is resolved on open), drop its cached embedding + any text-hash-keyed score, and invalidate the renderer query that reads that posting. Otherwise the next score reuses the stale snippet embedding and the UI keeps showing the truncated text (#486).
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 · 40 lines · 88 tokens per session scan A f1068a222a2d
job-match-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 88 tokens to every session and 1,272 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.
treatment-plans
Format and structurally validate local treatment-plan documentation after clinical decisions have already been supplied and verified by authorized licensed professionals. Use for source traceability, clinician-authored intervention records, goals and checkpoints, shared-decision records, reconciliation handoffs, and…
resume-builder
Generate professional resumes that conform to the Reactive Resume schema. Use when the user wants to create, build, or generate a resume through conversational AI, or asks about resume structure, sections, or content. This skill guides the agent to ask clarifying questions, avoid hallucination, and produce valid JSON…
cloud-service-agreement
Draft and fill SaaS agreement templates — cloud contract, MSA, order form, software license, pilot agreement, design partner agreement. Includes variants with SLAs and AI terms. Produces signable DOCX from Common Paper standard forms. Use when user says "SaaS agreement," "cloud contract," "MSA," "order form,"…
diagramar-peca
Transforma qualquer peça já escrita (.md ou texto) em um PDF bem diagramado, com Legal Design simples — capa, destaques, citações em bloco, fundamentos e linha do tempo. Não altera o conteúdo, só a forma visual. Use quando quiser entregar uma petição, contrato, parecer ou notificação com aparência profissional e…
redlining-content
Use when the user asks to redline, track changes, or compare differences in a file. Compares an uploaded .docx or .pdf against a provided .dotx/.docx template and returns a redlined .docx where every textual difference is a Word tracked change (insertion/deletion) authored by "Copilot Studio AI". No visual conversion…