db-update

db-update is a skill for Claude Code from leopu00/job-hunter-team. It costs 61 tokens per session (2,170 once invoked), scanned A, original, MIT.

A command-line helper for changing existing JHT database records, such as job positions and applications. It does not create new records; that is handled by a separate insert tool.

In plain words
What is it for?
It helps mark jobs as checked or excluded, record liveness checks and salaries, add review results, and mark applications as sent.
Why use it?
It prevents accidental creation or blind overwriting and requires the current record to be checked before changing it.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 /app/shared/skills/db_update.py <table> <id> --<field> <value> [--<field> <value>...].

Good fit It helps mark jobs as checked or excluded, record liveness checks and salaries, add review results, and mark applications as sent.

Compare 6 skills from other repositories ↓
Install

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.

Clone the repo
git clone --depth 1 https://github.com/leopu00/job-hunter-team
agentmods
npx agentmods add skills/leopu00/job-hunter-team/db-update

Made for: Claude Code.

Wrote 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.

agentmods badge for db-update

README.md
[![agentmods](https://agentmods.dev/badge/skills/leopu00/job-hunter-team/db-update/github.svg)](https://agentmods.dev/skills/leopu00/job-hunter-team/db-update)
Your own site
<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/db-update"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/db-update/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.

agentmods 80×15 button for db-update

Your own site · 80×15
<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/db-update"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/db-update.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,170 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00061 $0.02170
Opus 5 $0.00030 $0.01085
Sonnet 5 $0.00012 $0.00434
Haiku 4.5 $0.00006 $0.00217

Measured 11d ago against content hash 0980c41a4394, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

db-update 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.

agents/_skills/db-update/SKILL.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

db-update — record updates on the JHT DB

Wrapper at /app/shared/skills/db_update.py. Updates specific fields on existing records. Does not create records — for that, see db-insert.

General pattern

python3 /app/shared/skills/db_update.py <table> <id> --<field> <value> [--<field> <value>...]

Tables: position, application.

Positions

# Promote to checked / excluded (Analyst's job)
python3 /app/shared/skills/db_update.py position 42 --status checked
python3 /app/shared/skills/db_update.py position 42 --status excluded

# last-checked marker (link confirmed alive — also used as anti-collision claim)
python3 /app/shared/skills/db_update.py position 42 --last-checked now

# Liveness: --is-open / --last-open-check also advance last_checked on
# their own, so a rechecked position leaves the care queue (which gates on
# the most recent of the two dates). Pass --last-checked only to override it.
python3 /app/shared/skills/db_update.py position 42 --is-open false --last-open-check now

# Salary as declared in the JD
python3 /app/shared/skills/db_update.py position 42 --salary-declared-min 40000 --salary-declared-max 55000

# Estimated salary (glassdoor / levels.fyi / analyst's estimate)
python3 /app/shared/skills/db_update.py position 42 --salary-estimated-min 35000 --salary-estimated-max 50000 --salary-estimated-source glassdoor

# Role family (categoria semantica).
python3 /app/shared/skills/db_update.py position 42 --role-family "Technical Writing"

# Location strutturata (Analyst). Pieno esempio per "Dublin, Ireland" hybrid:
python3 /app/shared/skills/db_update.py position 42 \
  --loc-city "Dublin" --loc-region "Leinster" \
  --loc-country "Ireland" --loc-country-code "IE" \
  --loc-continent "Europe" \
  --work-mode "hybrid" \
  --work-country "Ireland" --work-country-code "IE" \
  --is-multi-location false

# Esempi casi speciali:
# A) "Europe Remote" → country=NULL, continent=EU, work_country dall'HQ azienda
python3 /app/shared/skills/db_update.py position 42 \
  --loc-continent "Europe" --work-mode "remote" \
  --work-country "United States" --work-country-code "US" \
  --location-notes "Remote within EU, US-based company"

# B) "Italy" + full_remote
python3 /app/shared/skills/db_update.py position 42 \
  --loc-country "Italy" --loc-country-code "IT" --loc-continent "Europe" \
  --work-mode "remote" --work-country "Italy" --work-country-code "IT"

# E) Multi-location stesso paese ("Barcelona / Malaga")
python3 /app/shared/skills/db_update.py position 42 \
  --loc-country "Spain" --loc-country-code "ES" --loc-continent "Europe" \
  --work-mode "hybrid" --work-country "Spain" --work-country-code "ES" \
  --is-multi-location true --location-notes "Barcelona or Málaga (candidato sceglie)"

# Per "ripulire" un campo (set NULL) passa stringa vuota:
python3 /app/shared/skills/db_update.py position 42 --loc-city ""

Read the full file on GitHub · 172 lines

Files

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.

Changes

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.

  1. 11d ago First seen · 172 lines · 61 tokens per session scan A 0980c41a4394

Subscribe to this mod's changes

db-update is a skill published in the GitHub repository leopu00/job-hunter-team (49 stars, last pushed yesterday), licensed MIT. It adds 61 tokens to every session and 2,170 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.