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/sentinel-ordersWrote 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/sentinel-orders)<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/sentinel-orders"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/sentinel-orders/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/sentinel-orders"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/sentinel-orders.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 7 findings, 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 Rogue Agent · line 47 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Prompt Injection · line 53 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
- medium Prompt Injection · line 65 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
- medium Prompt Injection · line 71 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
- medium Prompt Injection · line 60 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
- medium Prompt Injection · line 97 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
- medium Prompt Injection · line 82 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 | $0.00118 | $0.02839 |
| Opus 5 | $0.00059 | $0.01419 |
| Sonnet 5 | $0.00024 | $0.00568 |
| Haiku 4.5 | $0.00012 | $0.00284 |
Grade A, and why
sentinel-orders 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sentinel-orders — react to the watchdog
The Sentinel emits a tick every ~5 min and converts usage + velocity (vel_team vs vel_target) + weekly into one of the orders below. Each order maps to a precise action. Stick to the mapping; do not improvise. NB: proj nel tick è INFO volatile (oscilla ±400pt) — NON è il trigger; usa vel_team vs vel_target + usage vs target + weekly.
Throttle table (config-driven)
The Sentinel sends a Throttle: N level. You translate it into per-agent durations in $JHT_HOME/config/throttle.json. Agents read that file via jht-throttle --agent <name> — one atomic write fans out to the whole team.
| Level | Pause | Extra actions |
|---|---|---|
| 0 full speed | 0s | no restriction; spawn allowed if backlog requires it |
| 1 light | 30s | no spawn |
| 2 moderate | 120s | + stop one extra instance (e.g. SCRITTORE-2) |
| 3 heavy | 300s | + keep one instance per role |
| 4 near-freeze | 600s | + ESC current actions, no spawn |
python3 /app/shared/skills/throttle-config.py set scout-1 60
python3 /app/shared/skills/throttle-config.py bulk-set \
scout-1=300 scrittore-1=60 analista-1=0 scorer-1=0 critico=0
python3 /app/shared/skills/throttle-config.py dump # full state
python3 /app/shared/skills/throttle-config.py reset # all to 0
Use bulk-set when you want differentiated values per agent based on individual consumption (cross-check with token-rate-now if you need to see who is dominating right now).
🎯 The level in the table is not the value you write.
Throttle: Nis one number for the whole team;throttle.jsonholds one value per agent, and choosing the split is yours alone — no script moves the worker throttle any more. The arithmetic lives inthrottle-distribution: whose share the cut comes from (the top-burn pays; the Analista and the Scorer, the two roles that turn a backlog into a position with a score, are the last you touch), how many seconds that is on the ladder, and when the right move is to leave it alone. Giving every agent the same number is exactly the failure that skill exists to prevent — it spends the brake where there was nothing to gain and takes throughput where it costs the most.
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 · 130 lines · 118 tokens per session scan A e835b2e16bed
sentinel-orders is a skill published in the GitHub repository leopu00/job-hunter-team (49 stars, last pushed yesterday), licensed MIT. It adds 118 tokens to every session and 2,839 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.