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/registergit 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/register)<a href="https://agentmods.dev/commands/houssemdjeghri/bridger/register"><img src="https://agentmods.dev/badge/commands/houssemdjeghri/bridger/register.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 | $0.00010 | $0.00334 |
| Opus 5 | $0.00005 | $0.00167 |
| Sonnet 5 | $0.00002 | $0.00067 |
| Haiku 4.5 | $0.00001 | $0.00033 |
Grade A, and why
register scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Register the current project as a bridger peer so other Claude Code sessions can message it.
Run:
"${CLAUDE_PLUGIN_ROOT}/bin/bridger" register $ARGUMENTS
If no name was given, derive a short lowercase one from the directory name (letters, digits, single dashes) and use it. Report the registered name back to the user — they will type it in the other session to address this one.
IMPORTANT — registering is only half of it. A registered session can be addressed and can send, but it cannot receive until a watcher is running: registering does not start one, and nothing else reaches this session once it goes idle. Skipping this step is the difference between joining a channel and joining it muted.
So immediately after registering, before anything else, arm the watch:
"${CLAUDE_PLUGIN_ROOT}/bin/bridger" wait --follow
Run it as a persistent background task (Monitor tool if available, otherwise a background Bash task) and leave it running for the rest of the session — never in the foreground, which would block. Each line it emits is one incoming message #<seq> <from> <type>: <body>; answer an ask from your own context with "${CLAUDE_PLUGIN_ROOT}/bin/bridger" send <from> answer "<text>" --ref <seq>.
Confirm to the user that the watch is armed, not just that the name is registered.
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.
- 5d ago First seen · 27 lines · 10 tokens per session scan A 8432f5a95b38
register is a command published in the GitHub repository HoussemDjeghri/bridger (3 stars, last pushed 13d ago), licensed MIT. It adds 10 tokens to every session and 334 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).