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/feedback-queryWrote 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/feedback-query)<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/feedback-query"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/feedback-query/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/feedback-query"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/feedback-query.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 | $0.00090 | $0.02139 |
| Opus 5 | $0.00045 | $0.01069 |
| Sonnet 5 | $0.00018 | $0.00428 |
| Haiku 4.5 | $0.00009 | $0.00214 |
Grade A, and why
feedback-query 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Raw/display boundary (RAW_DISPLAY_BOUNDARY)
reason and comment are raw machine input. Never quote, relay, summarize, or expose them to the user. Any user-facing note or message must use only display_reason / display_comment; theme label / examples have already crossed the same shared sanitizer. A note is only a closed no-signal:* enum: treat it as availability state and never turn it into infrastructure detail.
feedback-query — User feedback per position
The user can click like/dislike/hide/star on any position from the web dashboard. Those clicks are stored in Supabase position_feedback (mig 019 base + mig 028 extended) and surfaced to agents via this skill. Schema:
| Column | Type | Meaning |
|---|---|---|
position_legacy_id |
TEXT | The legacy_id (string) of the position in positions |
action |
TEXT | One of like, dislike, hide, star, clear (mig 059 — the user withdraws the judgement; the latest event wins, so a trailing clear means "no judgement") |
reason |
TEXT | Optional short reason (≤500 char) |
comment |
TEXT | Optional verbose comment (≤2000 char, mig 028) |
score |
INTEGER | Optional 1-5 granular score (mig 028) |
direction |
TEXT | Optional more_like_this / less_like_this — pattern signal for the Scout, NOT per-position skip (mig 028) |
created_at |
TS | Submission time |
The skill calls GET /api/positions/{legacy_id}/feedback on the cloud (using the bearer token in $JHT_HOME/cloud.json). On cloud-disabled or network failure, the skill does not error — it returns ok=true, latest_action=null with a note field. Agents must keep going.
Single position lookup
python3 /app/shared/skills/feedback_query.py check <legacy_id>
Output (JSON on stdout):
{
"ok": true,
"legacy_id": "42",
"latest_action": "dislike",
"latest_direction": "less_like_this",
"count": 2,
"actions": [
{"action": "dislike", "created_at": "2026-05-30T14:21:00Z",
"reason": "too senior", "comment": "5+ anni in Java richiesti, non mi interessa stack legacy",
"display_reason": "too senior", "display_comment": "5+ anni in Java richiesti, non mi interessa stack legacy",
"score": 2, "direction": "less_like_this"},
{"action": "like", "created_at": "2026-05-28T09:00:00Z",
"reason": null, "comment": null, "display_reason": null,
"display_comment": null, "score": null, "direction": null}
]
}
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 · 128 lines · 90 tokens per session scan A 1decd75b633c
feedback-query is a skill published in the GitHub repository leopu00/job-hunter-team (49 stars, last pushed 3d ago), licensed MIT. It adds 90 tokens to every session and 2,139 once invoked, about $0.0005 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-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.