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/scout-coordWrote 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/scout-coord)<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/scout-coord"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/scout-coord/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/scout-coord"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/scout-coord.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Excessive Agency · line 111 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 | $0.00089 | $0.01981 |
| Opus 5 | $0.00044 | $0.00991 |
| Sonnet 5 | $0.00018 | $0.00396 |
| Haiku 4.5 | $0.00009 | $0.00198 |
Grade A, and why
scout-coord 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
scout-coord — partition the territory
Multiple Scouts run in parallel (max 2 instances by team policy). The team works only if they agree on a non-overlapping partition of:
- which circles each owns (1 = primary preference, 2 = geo neighbours, 3 = relocation, 4 = satellite, 5 = frontier)
- which source tiers each owns (LinkedIn / ATS aggregators / niche / WebSearch)
The state lives in the shared SQLite database managed by scout_coord.py; the scouts negotiate via tmux at boot and persist the agreement there.
One database, or no coordination at all. All Scouts must be on the same database — the team's own jobs.db, the same JHT_DB every other skill uses (the launcher already exports it to your pane). There is no separate coordination file to resolve anymore; an old scout_coordination.db, if one exists, is imported once at bootstrap and left in place, read-only from then on. If it exits 3, the database is unusable: report the message it printed and STOP. Never create a database of your own, never point the tool at another path.
# Which database am I actually on?
python3 /app/shared/skills/scout_coord.py doctor
Step 1 — Discover peers
tmux list-sessions 2>/dev/null | awk -F: '{print $1}' | grep -E '^SCOUT-[0-9]+$'
If you are the only scout listed → no negotiation needed, claim everything you can handle. Skip to Step 4.
If others are listed → you must negotiate (Steps 2-3) before scraping anything.
Step 2 — Reset stale state
If the previous scout team crashed mid-loop, scout_coord.py may hold stale assignments referring to dead sessions. Wipe them:
python3 /app/shared/skills/scout_coord.py reset
This is a coordinated step: the lowest-numbered live SCOUT (usually SCOUT-1) does the reset, the others wait. Announce it on tmux:
jht-tmux-send SCOUT-2 "[@$MY_ID -> @scout-2] [INFO] resetto scout_coord, attendi 5s prima di assign"
Step 3 — Negotiate via tmux
Open a short conversation (3-5 messages max) with each peer. Propose a split:
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 · 132 lines · 89 tokens per session scan A 7b5642b6a504
scout-coord is a skill published in the GitHub repository leopu00/job-hunter-team (49 stars, last pushed yesterday), licensed MIT. It adds 89 tokens to every session and 1,981 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-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.