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/py-tools-auditWrote 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/py-tools-audit)<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/py-tools-audit"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/py-tools-audit/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/py-tools-audit"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/py-tools-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
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 →
- high Memory Poisoning · line 109 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
- medium Privilege Escalation · line 123 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
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 | $0.00143 | $0.01717 |
| Opus 5 | $0.00072 | $0.00859 |
| Sonnet 5 | $0.00029 | $0.00343 |
| Haiku 4.5 | $0.00014 | $0.00172 |
Grade A, and why
py-tools-audit scanned grade A with 1 finding 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.
Asks for rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- **Never sudo-uninstall.** Stay inside `uv pip uninstall --user`. T13 forbids `sudo pip` for the same reason it forbids `sudo pip install`. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
py-tools-audit — clean the shared Python magazzino
$JHT_HOME/.local/lib/python3.x/site-packages/ is the single shared user-base every agent reads from (T13). Any agent can uv pip install --user <pkg> when it needs a library, but agents don't uninstall when they later switch approach — packages pile up. Roughly weekly the magazzino crosses 800 MB and needs a coordinated audit.
The audit is coordinated because a static import grep can miss libraries loaded dynamically at runtime (e.g. a tools/ script the Writer calls only when a JD asks for a specific format). Hence: ask before removing.
Trigger
- ⏰ ~weekly (every 7 days of continuous run), at the start of an idle operational day
- 📈 on-demand when
du -sh /jht_home/.local> 800 MB - 🚀 before a major release / handoff to the user
Two-round flow (because the Dottore is one-shot)
Round N: audit → broadcast candidates → leave state file
…30 min…
Round N+1: collect answers → compute keep_set → uninstall → re-audit → report
Each round logs its phase in $JHT_HOME/logs/py-audit-state.json:
{"phase": "broadcast_sent", "round_id": "...", "ts": "ISO-UTC",
"candidates": ["pymupdf", "pdfminer.six", "reportlab", "..."],
"broadcast_at": "ISO-UTC"}
When you wake up, check this file first:
- file missing or
phase=done→ fresh round, go to "Round N" below phase=broadcast_sentandnow - broadcast_at >= 1h→ "Round N+1" belowphase=broadcast_sentandnow - broadcast_at < 1h→ consent window not yet closed, skip the audit this round
Round N — start the audit
1. Threshold check
python3 /app/shared/skills/py_tools_audit.py --threshold-mb 800
- Exit
0→ nothing urgent. Stop here, do not broadcast. - Exit
2→ it's worth cleaning. The script also prints the candidates table — packages with no active import, excluding the whitelist (transitive deps + pinned binary CLIs).
2. Broadcast to every agent
Send one [PY-AUDIT] message to each live agent session via jht-tmux-send:
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 · 137 lines · 143 tokens per session scan A 15cd0672bf36
py-tools-audit is a skill published in the GitHub repository leopu00/job-hunter-team (49 stars, last pushed yesterday), licensed MIT. It adds 143 tokens to every session and 1,717 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (asks for root). 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.