Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/leopu00/job-hunter-teamnpx agentmods add skills/leopu00/job-hunter-team/position-insertWrote 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/leopu00/job-hunter-team/position-insert)<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/position-insert"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/position-insert.svg" alt="Measured on agentmods" 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 | $0.00108 | $0.02590 |
| Opus 5 | $0.00054 | $0.01295 |
| Sonnet 5 | $0.00022 | $0.00518 |
| Haiku 4.5 | $0.00011 | $0.00259 |
Grade C, and why
position-insert scanned grade C with 2 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 8d 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.
Cloud metadata endpointhighServer-side request forgery
One request to 169.254.169.254 can return temporary IAM credentials.
> `169.254.169.254` is not a job page. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
> `safe_fetch.py` replaces `curl -L` on purpose: it checks **every** How it starts
The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
position-insert — 5 gates per position
A position is worth inserting only if all five gates pass. The order matters: the cheaper checks come first so the expensive ones (full JD fetch + filtering) run only on viable candidates.
Gate 1 — Dedup (cheap, mandatory first)
python3 /app/shared/skills/db_query.py check-url <linkedin_id_or_url>
- Output
TROVATA→ SKIP (already in DB, possibly different status — never re-insert). - Output
NON TROVATA→ proceed to Gate 2.
The dedup key is the canonical URL (or LinkedIn job ID for LinkedIn). If the same posting comes from two different sources (e.g. company career page AND a LinkedIn cross-listing), check-url deduplicates.
Gate 2 — Link verification (HTTP + URL)
Two-step check to detect dead postings AND silent redirects to a generic /careers page (= job removed but page returns 200).
Step 2a — status code + final URL
python3 /app/shared/skills/safe_fetch.py --status '<URL>'
| Result | Action |
|---|---|
HTTP:404 / HTTP:410 |
SKIP (link morto) |
HTTP:301/302 to a generic /careers or /jobs |
SKIP (posizione rimossa, redirect generico) |
HTTP:200/301/302 final URL = posting page |
proceed to Step 2b |
Step 2b — content signals
python3 /app/shared/skills/safe_fetch.py '<URL>' \
| grep -i 'no longer accepting\|closed-job\|position has been filled\|expired\|job not found'
- Match → SKIP (closed job)
- No match → proceed to Gate 3
Workable note
For ATS hosted on Workable: there are two URLs per posting. Use the right one:
apply.workable.com/...→ apply form: returns302when the job is closed (looks like a dead link, false positive).jobs.workable.com/...→ canonical JD page: HTTP 200 + valid JSON-LD if the position is alive.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 202 lines · 108 tokens per session scan C 1f9462de3a6d
position-insert is a skill published in the GitHub repository leopu00/job-hunter-team (49 stars, last pushed yesterday), licensed MIT. It adds 108 tokens to every session and 2,590 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 2 findings (cloud metadata endpoint, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
database
A database design and migration guide written in Korean. It covers table structure, naming conventions, common columns, indexes, foreign keys, and versioned migration files.
db-migrate
Creates, checks the status of, and validates database migrations by auto-detecting the project's migration framework (Alembic, Prisma, Knex, Django, Rails/ActiveRecord, Flyway, Atlas, TypeORM, Sequelize, SQLx, golang-migrate, Liquibase) from marker files, then driving that framework's own CLI. Use when the user wants…
airtable
Airtable base management — records, views, and formulas via REST API.
landing-performance
Fix performance issues in apps/landing for leaderboards, battles, rankings, vote/reaction summaries, and high-cardinality result pages.
storage-steer
Prioritize hardening persistent storage mechanisms in scenarios/{{TARGET}}/ to ensure reliable, isolated, and professionally structured data persistence. This skill steers toward storage that is correctly configured, properly abstracted, and follows Vrooli resource conventions.
sql-database
Safe schema-aware SQL querying against CSV/Parquet/JSON files, SQLite databases, and live Postgres. Use when querying structured data, profiling a schema, or building data pipelines.