Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/houssemdjeghri/bridger/monitorgit clone --depth 1 https://github.com/HoussemDjeghri/bridgerWrote 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/commands/houssemdjeghri/bridger/monitor)<a href="https://agentmods.dev/commands/houssemdjeghri/bridger/monitor"><img src="https://agentmods.dev/badge/commands/houssemdjeghri/bridger/monitor.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00013 | $0.00337 |
| Opus 5 | $0.00006 | $0.00169 |
| Sonnet 5 | $0.00003 | $0.00067 |
| Haiku 4.5 | $0.00001 | $0.00034 |
Grade A, and why
monitor 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 4d 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.
What it actually says
If $ARGUMENTS contains --stop, run ONLY this and report what it prints —
--stop takes no other options, so passing it through the start block below
(which adds --no-open) is a usage error, not a stop:
"${CLAUDE_PLUGIN_ROOT}/bin/bridger" monitor --stop
Otherwise start the monitor as a background task, so this session stays usable:
"${CLAUDE_PLUGIN_ROOT}/bin/bridger" monitor --no-open $ARGUMENTS
Report the URL it prints (default http://127.0.0.1:8787) and tell the user to
open it. It serves on loopback only and needs python3.
The monitor is read-only: it parses the state files and never writes one, so it does not consume unread messages or advance any cursor. Leaving it running does not affect any session.
It outlives this session on purpose, so killing the background task is not how
you stop it — and once this session closes there is no background task left to
kill. Use the --stop block at the top, which stops the monitor(s) serving this
bus and leaves any monitor on another bus running. A monitor started without
--root (or owned by another user) cannot be attributed to a bus from its
command line; --stop reports those rather than guessing, and stops nothing.
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.
- 4d ago First seen · 33 lines · 0 tokens per session scan A 5fbfddff2c84
monitor is a command published in the GitHub repository HoussemDjeghri/bridger (3 stars, last pushed 12d ago), licensed MIT. It adds 13 tokens to every session and 337 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
wrap
You are closing a Claude Code session. Execute all steps below in order.
unwrap
You are resuming a Claude Code session. Execute all steps below in order — no confirmation needed.
wrap-find
Search session logs for a keyword or phrase. The search term is everything after /wrap-find in the user's message.
start
Start watching the current project with Bonsai.
discuss
Discuss a Bonsai observation in the current session.
mute
Silence Bonsai temporarily for this project (or all projects with --global).