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/bridge-mailboxWrote 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/bridge-mailbox)<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/bridge-mailbox"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/bridge-mailbox/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/bridge-mailbox"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/bridge-mailbox.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00111 | $0.00939 |
| Opus 5 | $0.00056 | $0.00469 |
| Sonnet 5 | $0.00022 | $0.00188 |
| Haiku 4.5 | $0.00011 | $0.00094 |
Grade A, and why
bridge-mailbox 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bridge-mailbox — recover missed verdicts
The bridge talks to you over tmux, but tmux delivery can fail silently during a long turn (Codex / Kimi TUI render issues, you were inside a long tool call, etc.). To make sure no verdict is lost, the bridge also appends every tick to a JSONL mailbox at $JHT_HOME/logs/bridge-mailbox.jsonl. You drain it at the top of every turn.
The mandatory first action
Before anything else — before reading messages, before deciding actions, before opening another skill — run:
python3 /app/shared/skills/bridge_mailbox.py drain
Possible outputs:
no pending verdicts→ mailbox empty, proceed with the turn normally.- one or more lines formatted as live tmux ticks (
[BRIDGE PACING] ...,PIPELINE STALLED ...,[BRIDGE ALERT] ...).
drain consumes the entries (they are marked read on success) — re-running it returns no pending verdicts until the bridge appends new ones.
How to apply drained verdicts
Process ALL the lines, but act only on the last one. The earlier ones are already stale — the metrics have moved since. Two exceptions where an earlier line still matters:
PIPELINE STALLEDrecent (< 30 min) and still pertinent (proj is still low, team_kt is still low right now). Act on the playbook (re-light the pipeline upstream) even if a later valid[BRIDGE PACING]arrived after it. Stalls are state, not events — they need clearing, not just measuring.- A
[PAUSA TEAM]/[HARD FREEZE]you missed. If one is in the queue and you have not yet sent[RIPRENDI], the team is still frozen — handle it withsentinel-ordersbefore the latest pacing.
For the routine case (one or more [BRIDGE PACING] lines):
- read each line to keep the temporal context (you can see how the trend evolved while you were busy)
- open the
bridge-pacingskill once and apply only the last verdict's calibration
Other commands (debug / inspection)
python3 /app/shared/skills/bridge_mailbox.py status # how many pending vs total
python3 /app/shared/skills/bridge_mailbox.py peek # read without consuming
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 · 57 lines · 111 tokens per session scan A 1d8dc2890325
bridge-mailbox is a skill published in the GitHub repository leopu00/job-hunter-team (49 stars, last pushed yesterday), licensed MIT. It adds 111 tokens to every session and 939 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.