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/salary-estimateWrote 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/salary-estimate)<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/salary-estimate"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/salary-estimate/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/leopu00/job-hunter-team/salary-estimate"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/salary-estimate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 129 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 132 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00014 | $0.01497 |
| Opus 5 | $0.00007 | $0.00749 |
| Sonnet 5 | $0.00003 | $0.00299 |
| Haiku 4.5 | $0.00001 | $0.00150 |
Grade A, and why
salary-estimate 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 12d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
salary-estimate — hierarchical estimate with a local cache
Why it exists
Snapshot 2026-05-17 (43 Kimi scores): 41 scores out of 43 with
salary_fit=5/10 (the "no data no bias" default), 2 with real values from
an explicit JD. Result: salary_fit (weight 10/100) was de facto
inert — the Scorer's decision space shrunk from 100 to 95.
Cause: nobody was populating salary_estimated_*. The Scorer is honest,
it does not make things up, and with no data it falls back to the default.
User decision: build a local cache of the estimates, so the first fetch
costs and the following ones are free. "Salaries do not change from week
to week, they change from year to year".
4 levels (in order, stop at the first one that produces a range)
LEVEL 1 — Declared range (position)
If positions.salary_declared_min and salary_declared_max are not NULL →
use those, no estimate. The Scrittore can call:
python3 /app/shared/skills/salary_estimate.py --position-id 42
The script reads the declared values from the DB and returns level=1 with
the numbers.
LEVEL 2 — Local cache
Path: /jht_home/.cache/salary_estimates.json. Key:
(stack, seniority, country, mode). TTL 30 days.
python3 /app/shared/skills/salary_estimate.py \
--stack python --seniority junior --country IT --mode remote
Hit → JSON with level=2, source=cache, min, max. Miss → falls through to
L3 or L4.
LEVEL 3 — Web search (stub, depends on F-2)
For now it returns None: the skill falls straight through to L4. Once F-2 (Scout web access) is available, the Scout/Analista will populate the cache via web search on Glassdoor/Levels/Indeed. From then on the first lookup of a new combination does a single fetch, then 29 days of free hits.
LEVEL 4 — Neutral default + flag
If every level above fails → it returns level=4, min=null, max=null, estimation_failed=true, reason="no_data_default". The Scorer
sets salary_fit=5 AND adds no_data_default to score.notes — so that
the Mentor (downstream) does not propagate the 5 as a real datum but as
"N/A" (see bug #27, Mentor fix).
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.
- 12d ago First seen · 134 lines · 14 tokens per session scan A 641474565617
salary-estimate is a skill published in the GitHub repository leopu00/job-hunter-team (49 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 1,497 once invoked, about $0.0001 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 skills, from other repositories
recipe-create-expense-tracker
Set up a Google Sheets spreadsheet for tracking expenses with headers and initial entries.
stripe
Generated by Gutenberg. Use this skill to call the stripe API through the local stripe CLI.
coingecko
Generated by Gutenberg. Use this skill to call the coingecko API through the local coingecko CLI.
exchange-rates
Generated by Gutenberg. Use this skill to call the exchange-rates API through the local exchange-rates CLI.
finance-report-explainer
Plain-language explanation of a finance report with audience-aware framing. Analysis only — not certified advice.
finance-analyst
Explains financial reports, KPI movement, budget scenarios, and revenue experiments without pretending to provide certified advice.