Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add HoussemDjeghri/bridger/plugin install 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/peers)<a href="https://agentmods.dev/commands/houssemdjeghri/bridger/peers"><img src="https://agentmods.dev/badge/commands/houssemdjeghri/bridger/peers/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/commands/houssemdjeghri/bridger/peers"><img src="https://agentmods.dev/badge/commands/houssemdjeghri/bridger/peers.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00016 | $0.00548 |
| Opus 5 | $0.00008 | $0.00274 |
| Sonnet 5 | $0.00003 | $0.00110 |
| Haiku 4.5 | $0.00002 | $0.00055 |
Grade A, and why
peers scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
"${CLAUDE_PLUGIN_ROOT}/bin/bridger" peers
Show the output to the user. Each line is name [status] directory @branch — summary.
For listening and queued, the status column is watcher liveness, not
reachability. listening means that session's watcher is running. queued
means it is not — which covers both a closed session and a live one that never
armed a watch, since registering does not start one. A queued peer is still
registered, still addressable, and still receives; it may just read the message
later. Never report either of those as unreachable from this column alone —
that is what ask <peer> --timeout tests.
missing is queued plus two facts: that peer's registered directory no longer
exists, and no watcher process is running for the name (a watcher still running
keeps it queued, because someone is demonstrably there).
A missing peer is still addressable and still receives, and it is NOT proof
the peer is dead — a session whose worktree was removed keeps its working directory and
goes on polling and sending, so it may well read the message. Treat it as a
normal peer; do not skip it and do not report it as unreachable.
departed never appears here, and is the one status that is NOT an address:
that name has no registration at all (it ran bridger leave, or reap --force
dropped it), so send to it fails. It shows up in bridger status instead,
because its thread is kept — anything it sent still arrives on the next poll,
and bridger log <name> reads the history. Never confuse it with missing:
missing still receives, departed cannot.
What missing usually means is a leftover registration from a deleted worktree.
If the user asks about one, or several show up, offer to run bridger reap — it lists
each one with how much unread mail it still holds. bridger reap --force drops
them, keeping their threads as history. Point out the unread counts before
dropping anything: a session still open in a removed directory cannot be
detected, and dropping its registration strands its mail for good.
If the current directory is not registered, offer /bridger:register <name> —
the bridger is opt-in, so only registered directories appear here.
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 · 44 lines · 16 tokens per session scan A 4906e0b376cf
peers is a command published in the GitHub repository HoussemDjeghri/bridger (3 stars, last pushed 17d ago), licensed MIT. It adds 16 tokens to every session and 548 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).