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/cv-structureWrote 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/cv-structure)<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/cv-structure"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/cv-structure/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/cv-structure"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/cv-structure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
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 →
- high Anti-Refusal · line 37 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
- high Anti-Refusal · line 117 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
- medium Prompt Injection · line 31 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00000 | $0.05003 |
| Opus 5 | $0.00000 | $0.02501 |
| Sonnet 5 | $0.00000 | $0.01001 |
| Haiku 4.5 | $0.00000 | $0.00500 |
Grade A, and why
cv-structure 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 — 336 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cv-structure — the canonical CV layout
Output goes to $JHT_USER_DIR/cv/CV_<Candidato>_<Company>.md (then PDF via pandoc/typst). Path rule: application-flow skill — never write the final CV under $JHT_AGENT_DIR (that's scratch only, T11).
<Candidato> = Nome_Cognome from the profile. <Company> = company name normalised PascalCase, no spaces or slashes (e.g. Acme_Corp → AcmeCorp).
Before you write: read the source, match the register (W-05, 2026-07-01)
candidate_profile.yml is flattened data, not voice. Before drafting, read the user's original CV in $JHT_HOME/profile/sources/ (the PDF/doc they uploaded) plus $JHT_HOME/profile/summaries/. Two reasons:
- Voice & distinctive detail. The original carries what makes the candidate them — the story, the named context, the human register. A CV rebuilt from the
.ymlalone comes out cold and interchangeable. Mirror their phrasing and keep the concrete details that give weight (not a bare "VIP guest handling" but the Nobu / De Niro–founded context behind it). - Register by industry. Read
industry+seniority_targetfrom the profile. This skill's defaults (metric-in-bold + tech-in-parens, a "Technical Skills" table withPython, Go, Bash) are tuned for tech / engineering roles. For client-facing / non-tech profiles they are WRONG — they sterilise the exact warmth that sells the candidate. Adapt:
| Profile family | Section 4 name | Bullet style | About Me |
|---|---|---|---|
| Tech / engineering | Technical Skills (Languages, Backend, Data, Infra) | metric in bold + tech in parens | factual, numbers |
| Client-facing / hospitality / retail / care | Skills & Strengths (NO programming languages) | concrete result + context in parens (place, scale, clientele); warmth allowed | credible + a human touch, mirroring the original |
| Sales / business | Core Skills | metric in bold (revenue, targets) + tools in parens | outcome-driven |
| Creative / design | Skills & Tools + portfolio link | outcome + medium in parens | voice-forward |
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 · 336 lines · 0 tokens per session scan A 99c0632b6f5b
cv-structure is a skill published in the GitHub repository leopu00/job-hunter-team (49 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,003 tokens. 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
persona-event-coordinator
Plan and manage events — scheduling, invitations, and logistics.
persona-team-lead
Lead a team — run standups, coordinate tasks, and communicate.
persona-researcher
Organize research — manage references, notes, and collaboration.
recipe-save-email-attachments
Find Gmail messages with attachments and save them to a Google Drive folder.
recipe-draft-email-from-doc
Read content from a Google Doc and use it as the body of a Gmail message.
recipe-review-meet-participants
Review who attended a Google Meet conference and for how long.