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/mentor-patternsWrote 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/mentor-patterns)<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/mentor-patterns"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/mentor-patterns/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/mentor-patterns"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/mentor-patterns.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00075 | $0.03567 |
| Opus 5 | $0.00037 | $0.01784 |
| Sonnet 5 | $0.00015 | $0.00713 |
| Haiku 4.5 | $0.00007 | $0.00357 |
Grade A, and why
mentor-patterns 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 10d 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 — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mentor-patterns — what the records reveal
The Mentor watches sets, not single points. Six patterns are worth speaking about; everything else is noise.
Pattern A — Skill gap between profile and market
Skills that show up repeatedly in JD requirements but are absent from candidate_profile.yml > skills. If they also appear in high-scoring positions, the gap is costly (closing it would unlock submissions, not noise).
Detection
# 1. Pull the last 30 positions with their requirements + score
python3 /app/shared/skills/db_query.py positions --limit 30 \
--status scored,checked --order-by created_at:desc
# 2. Tokenise requirements, compare with profile.skills.primary + .secondary
# 3. Count tokens NOT in profile that appear in N positions
Threshold
Speak only if a missing skill appears in ≥ 5 positions in the last 30 AND ≥ 1 of them has score ≥ 65 (within reach of the submission gate).
Example output
", I have counted. Docker appears in twelve of the last thirty positions in the records. Nine scored between 65 and 78 — within reach of the submission gate, never crossing it. One craft separates you from a third of the path before you."
Pattern B — Recurring exclusions
Counts of ESCLUSA: [TAG] markers in positions.notes over the last 30 days. If one tag dominates, the search direction is misaligned.
Detection
python3 /app/shared/skills/db_query.py positions --status excluded --limit 50 \
--order-by last_checked:desc \
| grep -oE 'ESCLUSA: \[(SENIORITY|STACK|GEO|LINGUA|LINK_MORTO|SCAM)\]' \
| sort | uniq -c | sort -rn
Threshold
Speak only if one tag accounts for ≥ 40% of exclusions AND total exclusions ≥ 20 in the last 30 days.
Interpretation
| Dominant tag | Likely cause | Suggested move |
|---|---|---|
[SENIORITY] |
Aiming too high (or too low) for the candidate's level | Adjust seniority_target in profile |
[LINGUA] |
A single language is closing entire markets | Add the language, or shrink geographic scope |
[GEO] |
work_mode / relocation out of step with the search |
Re-discuss preferences with the user |
[STACK] |
Adjacent-stack noise reaching the team | Tighten Scout filters via Capitano |
[LINK_MORTO] (>40%) |
Source quality issue, not candidate issue | Forward to Capitano, this is a Scout problem |
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.
- 10d ago First seen · 239 lines · 75 tokens per session scan A 0e4901aaef00
mentor-patterns is a skill published in the GitHub repository leopu00/job-hunter-team (49 stars, last pushed 2d ago), licensed MIT. It adds 75 tokens to every session and 3,567 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 2026-08-30.
Other skills, from other repositories
gws-drive
Google Drive: Manage files, folders, and shared drives.
gws-calendar
Google Calendar: Manage calendars and events.
gws-gmail-reply
Gmail: Reply to a message (handles threading automatically).
gws-gmail-send
Skill "gws-gmail-send" from googleworkspace/cli, covering gmail +send, usage, flags, examples and tips.
gws-calendar-insert
Google Calendar: Create a new event.
gws-gmail-watch
Gmail: Watch for new emails and stream them as NDJSON.