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/stevengonsalvez/agents-in-a-boxnpx agentmods add skills/stevengonsalvez/agents-in-a-box/bridgeWrote 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/stevengonsalvez/agents-in-a-box/bridge)<a href="https://agentmods.dev/skills/stevengonsalvez/agents-in-a-box/bridge"><img src="https://agentmods.dev/badge/skills/stevengonsalvez/agents-in-a-box/bridge/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/stevengonsalvez/agents-in-a-box/bridge"><img src="https://agentmods.dev/badge/skills/stevengonsalvez/agents-in-a-box/bridge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 77 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00147 | $0.01580 |
| Opus 5 | $0.00073 | $0.00790 |
| Sonnet 5 | $0.00029 | $0.00316 |
| Haiku 4.5 | $0.00015 | $0.00158 |
Grade A, and why
ainb-fleet:bridge 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 12d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ainb fleet:bridge — native phone bridge
A single-binary, two-way relay between a chat channel and your ainb fleet. It folds every channel into the ainb binary — there is no separate Python runtime to install or manage. Three channels share ONE relay/routing core over one transport:
- Telegram — long-polling
getUpdatesover HTTP. - Slack — socket-mode WebSocket.
- Discord — raw Gateway WebSocket.
chat message ──▶ bridge ──parse target──▶ tmux send-keys ──▶ ainb session
reply ◀── bridge ◀──capture from JSONL transcript tail ◀──┘
This is ATC's voice to you: when ATC escalates, the NEED: … line surfaces in
whichever channel the bridge runs.
Subcommands
ainb fleet bridge run # start the daemon (default if no subcommand)
ainb fleet bridge install # install as a launchd/systemd service (idempotent)
ainb fleet bridge uninstall # remove the service unit (returns the removed path, if any)
ainb fleet bridge status # report INSTALL state of the service unit
run loads the config and drives every configured channel concurrently; it
runs until the process is stopped. bridge with no subcommand is the same as
bridge run.
statusreports INSTALL state, not liveness. For "is the bridge actually running and connected right now?" use/ainb-fleet:daemons— its heartbeat-backed probe distinguishes a live+connected bridge from a crashed one (stale heartbeat / recycled pid).bridge statusonly tells you whether the service unit is installed.
Config — ~/.agents-in-a-box/config/config.toml
At least ONE channel table must be present and valid. Tokens and ids are
resolved through ainb's secret resolver: a value may be a literal, a $ENV_VAR
ref, or a keychain:service ref — so the secret stays out of argv and out of
the launchd/systemd unit, read in-process only at startup. Config path honours
$AINB_CONFIG_PATH.
[fleet.bridge]
response_timeout = 300 # optional, seconds — shared default (per-channel overridable)
[fleet.bridge.telegram]
token = "$TELEGRAM_BOT_TOKEN" # or "keychain:svc" or a literal
user_id = 123456789 # authorized Telegram user id (integer)
default_target = "conductor" # optional: session to prefer when no name: prefix
require_mention_in_groups = true # optional, default true
response_timeout = 300 # optional, overrides the shared default
[fleet.bridge.slack]
bot_token = "$SLACK_BOT_TOKEN" # xoxb-… (Web API)
app_token = "$SLACK_APP_TOKEN" # xapp-… (socket-mode)
user_id = "U0123ABC" # authorized Slack user id (string)
default_target = "conductor" # optional
listen_mode = "mentions" # "mentions" (default) | "all"
response_timeout = 300 # optional
[fleet.bridge.discord]
token = "$DISCORD_BOT_TOKEN" # Bot token (gateway + REST), secret ref
user_id = "123456789012345678" # authorized Discord user id (snowflake string)
default_target = "conductor" # optional
channel_id = "123456789012345678" # optional fallback channel for replies
response_timeout = 300 # optional
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.
- 12d ago First seen · 146 lines · 147 tokens per session scan A cf174e4c66b3
ainb-fleet:bridge is a skill published in the GitHub repository stevengonsalvez/agents-in-a-box (23 stars, last pushed today), licensed MIT. It adds 147 tokens to every session and 1,580 once invoked, about $0.0007 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
chinese-git-workflow
A Git workflow guide tailored to Chinese-hosted platforms such as Gitee, Coding.net, and GitLab, including their code-review and build systems.
chinese-commit-conventions
A Chinese-language convention for writing Git commit messages, based on Conventional Commits, a standard format that tools can use to classify changes and build changelogs.
using-superpowers
A set of rules for finding and using assistant skills at the start of every conversation. It says to check for relevant skills before responding, including when asking a clarification question.
chinese-code-review
Chinese-language guidance for giving professional, tactful code-review feedback while still calling out real problems.
mcp-builder
A guide to building MCP servers, which let AI assistants call tools or read connected data. It covers server structure, tool design, validation, testing and deployment in TypeScript and Python.
platform-api
Queries the Genesys Cloud Platform API schema for endpoint details, permissions, parameters, and response formats. Use when user asks about Genesys Cloud API endpoints (e.g., "/api/v2/assistants/queues"), API documentation, API permissions, schemas, capabilities, or when implementing Genesys Cloud operations.