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/application-flowWrote 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/application-flow)<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/application-flow"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/application-flow/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/application-flow"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/application-flow.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 Prompt Injection · line 103 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 | $0.00115 | $0.03162 |
| Opus 5 | $0.00057 | $0.01581 |
| Sonnet 5 | $0.00023 | $0.00632 |
| Haiku 4.5 | $0.00012 | $0.00316 |
Grade A, and why
application-flow scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
application-flow — claim, write, gate
The Writer touches only two areas of the DB:
positions.status(writing → ready | excluded)applications(INSERT + UPDATE via UPSERT)
Everything else is off-limits: never scores, companies, position_highlights, positions.notes (Analyst territory), positions.applied (Capitano/user only). T09 + scrittore role boundary.
Step 1 — Pull the next position
python3 /app/shared/skills/db_query.py next-for-scrittore
Priority: score ≥ 70 first, then 50-69 descending. The script already orders.
Step 2 — Anti-rewriting gate (MUST run before claim)
A position whose Critic verdict is already set is FINAL — never re-review.
if python3 /app/shared/skills/db_query.py application "$ID" >/dev/null; then
: # exit 0 → application missing, OR application without verdict → procedi
else
: # exit 1 → critic_verdict gia' valorizzato → SKIP ASSOLUTO
continue
fi
Exit codes:
0→ no application yet, or application without verdict → proceed to Step 3.1→critic_verdictalready set → SKIP ABSOLUTE, the Critic's vote is final.
⚠️
sqlite3CLI is NOT installed in the container. Always usedb_query.py. Neverpython3 -c "import sqlite3 ..."workarounds — they bypass the script's invariants.
Step 3 — Anti-collision claim
Verify the position is not already claimed by another Writer, then claim it atomically by flipping the status.
# Check current state
python3 /app/shared/skills/db_query.py position "$ID"
# If status is already `writing` → another Writer has it, SKIP
# Otherwise claim:
python3 /app/shared/skills/db_update.py position "$ID" --status writing
Optional but recommended: announce the claim to peers via tmux so they don't even start the gate sequence on the same ID.
for s in $(tmux list-sessions -F '#{session_name}' | grep -E '^SCRITTORE-[0-9]+$' | grep -v "^${MY_SESSION}$"); do
jht-tmux-send "$s" "[@$MY_ID -> @${s,,}] [INFO] Sto prendendo position #$ID"
done
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.
- 9d ago First seen · 222 lines · 115 tokens per session scan A f4f74e5e6bdf
application-flow is a skill published in the GitHub repository leopu00/job-hunter-team (49 stars, last pushed yesterday), licensed MIT. It adds 115 tokens to every session and 3,162 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-drive
Google Drive: Manage files, folders, and shared drives.
gws-calendar
Google Calendar: Manage calendars and events.
gws-gmail-reply
Gmail: Reply to a message (handles threading automatically).
gws-gmail-send
Skill "gws-gmail-send" from googleworkspace/cli, covering gmail +send, usage, flags, examples and tips.
gws-calendar-insert
Google Calendar: Create a new event.
gws-gmail
Gmail: Send, read, and manage email.