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/session-refreshWrote 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/session-refresh)<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/session-refresh"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/session-refresh.svg" alt="Measured on agentmods" 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 | $0.00151 | $0.04632 |
| Opus 5 | $0.00076 | $0.02316 |
| Sonnet 5 | $0.00030 | $0.00926 |
| Haiku 4.5 | $0.00015 | $0.00463 |
Grade A, and why
session-refresh scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
session-refresh — clear agent context, keep continuity
You (the Dottore) are spawned at a scheduled slot (+30min from the work-window start, or at mid window). Your job this round is not liveness-pinging — it is to refresh the context of the active agent sessions: each long-running session accumulates a bloated context window; you summarize what it did, persist it, then recreate the session fresh and hand back the continuation.
Why this exists: the old Dottore burned ~51% of team budget pinging
[HEALTH]every 2h with zero useful checks. This round is rare (2×/window) and produces a durable, dense journal of the team's work.
Step 0 — window start (the analytics window)
WIN_START=$(python3 -c "import sys; sys.path.insert(0,'/app'); from shared.skills.working_hours import current_window_bounds as b; w=b(); print(w[0].isoformat() if w else '')")
# 24/7 (no window): fall back to the last 6h
[ -z "$WIN_START" ] && WIN_START=$(python3 -c "import datetime; print((datetime.datetime.now(datetime.timezone.utc)-datetime.timedelta(hours=6)).isoformat())")
ROUND_ID=$(date -u +%Y%m%dT%H%M%SZ)
DAY=$(date -u +%F)
JOURNAL=/jht_home/logs/doctor-retrospective.jsonl
ROUND_HEADS_UP_SENT=0
Step 1 — list sessions + age, decide order
tmux list-sessions -F '#{session_name}|#{session_created}'
- Order: worker sessions FIRST (
SCOUT-N · ANALISTA-N · SCORER-N · SCRITTORE-N · CRITICO-S*), coordinators LAST and with care (ASSISTENTE · MENTOR · SENTINELLA · CAPITANO). "With care" means capture their state well and compact them — NOT skip them (they are the top consumers; see Rules). Never refreshDOTTORE/DOCTOR-WATCHDOG(yourself / the scheduler). - FRESH skip (cheap pre-filter before the context check):
age = now - session_created. Ifage < 40 min→ SKIP entirely (nothing to summarize yet, and refreshing would throw away a session that just started). Logaction=skipped_fresh. Everything that survives this pre-filter goes through Step 1.4 (TTL) and then Step 1.5 (context check) — that>50%measurement, not age, is what decides the ordinary refresh.
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.
- 8d ago First seen · 185 lines · 151 tokens per session scan A 9222f6cb15f3
session-refresh is a skill published in the GitHub repository leopu00/job-hunter-team (49 stars, last pushed yesterday), licensed MIT. It adds 151 tokens to every session and 4,632 once invoked, about $0.0008 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-researcher
Organize research — manage references, notes, and collaboration.
persona-team-lead
Lead a team — run standups, coordinate tasks, and communicate.
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.