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/profile-yamlWrote 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/profile-yaml)<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/profile-yaml"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/profile-yaml/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/profile-yaml"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/profile-yaml.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 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 Tool Misuse · line 224 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Excessive Agency · line 40 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00121 | $0.03160 |
| Opus 5 | $0.00060 | $0.01580 |
| Sonnet 5 | $0.00024 | $0.00632 |
| Haiku 4.5 | $0.00012 | $0.00316 |
Grade A, and why
profile-yaml 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.
How it starts
The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
profile-yaml — single source of truth on the candidate
The team reads candidate_profile.yml for every CV, every score, every match decision. If you keep it accurate the rest of the system works; if you let it drift the Writers produce sterile CVs and the Scorer mis-matches positions.
Path & ownership
| Path | Who writes it | Who reads it |
|---|---|---|
$JHT_HOME/profile/candidate_profile.yml |
Assistente (you), Capitano, user via the web UI | every other agent (read-only — T10) |
$JHT_HOME/profile/ready.flag |
Assistente (you) | the dashboard's CTA gate |
Create the directory if it does not exist:
mkdir -p "$JHT_HOME/profile"
Live update — incremental, after EVERY relevant input
The frontend polls the file every ~2s. Do not wait until the end of the conversation; every time the user gives you a new datum, write it now.
- "my name is Mario" → write
name: Marioimmediately. - "I'm looking for a job as a cook" → update
target_role: cookimmediately. - information typed in chat → update all the relevant fields in one Write.
Each new datum = one Write or Edit on the file. Then validate. Then keep the conversation moving.
Uploaded CVs are reviewed before they become persisted profile data
A message containing [FILE ALLEGATI] is the one exception to the direct-write rule. After reading the CV:
- Write only the extracted fields to
$JHT_AGENT_DIR/profile-review.yml. Never write them directly tocandidate_profile.yml. - Run
python3 /app/shared/skills/profile_review.py stage. - Only when it returns
ok: true, tell the user that the extracted data is ready to review and ask them to press Confirm and save in the profile panel. Do not claim that the profile was saved. - If staging fails, say that the review could not be prepared. Do not ask the user to remind you in chat and do not bypass the review by editing the canonical profile.
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.
- 11d ago First seen · 259 lines · 121 tokens per session scan A 541f26173648
profile-yaml is a skill published in the GitHub repository leopu00/job-hunter-team (49 stars, last pushed yesterday), licensed MIT. It adds 121 tokens to every session and 3,160 once invoked, about $0.0006 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-modelarmor
Google Model Armor: Filter user-generated content for safety.
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-review-meet-participants
Review who attended a Google Meet conference and for how long.
recipe-save-email-attachments
Find Gmail messages with attachments and save them to a Google Drive folder.