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/askgit 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/ask)<a href="https://agentmods.dev/commands/houssemdjeghri/bridger/ask"><img src="https://agentmods.dev/badge/commands/houssemdjeghri/bridger/ask.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 | $0.00011 | $0.00316 |
| Opus 5 | $0.00005 | $0.00158 |
| Sonnet 5 | $0.00002 | $0.00063 |
| Haiku 4.5 | $0.00001 | $0.00032 |
Grade A, and why
ask scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Ask another session a question. The peer's agent answers from its own live conversation context.
The first word of the arguments is the peer name; the rest is the question. Rewrite the question in wire style before sending — telegraphic, exact identifiers, state the reply shape you want (see the bridger skill) — rather than forwarding the user's phrasing verbatim:
"${CLAUDE_PLUGIN_ROOT}/bin/bridger" ask <peer> "<question>" --json
Arguments: $ARGUMENTS
The command blocks until a reply referencing this question arrives, then prints it as JSON; relay the body to the user. Notes:
- If the reply's
typeisask, the peer needs more information before it can answer. Answer its question from your own context (read your own code if needed), send it back withbridger send <peer> answer "<text>" --ref <their seq>, and run the ask's wait again by polling for the final reply. - On timeout (exit 1), tell the user the peer did not respond — its session may not be listening (
/bridger:statusshows unread counts piling up). The wait defaults to 300s; a peer reasoning at high effort may need longer — pass--timeout <seconds>, or exportBRIDGER_ASK_TIMEOUTonce for a whole session.
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 · 23 lines · 11 tokens per session scan A 04cf679276cc
ask is a command published in the GitHub repository HoussemDjeghri/bridger (3 stars, last pushed 13d ago), licensed MIT. It adds 11 tokens to every session and 316 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).