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 skills add felipefontoura/bento --skill chatwootgit clone --depth 1 https://github.com/felipefontoura/bentoWrote 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/felipefontoura/bento/chatwoot)<a href="https://agentmods.dev/skills/felipefontoura/bento/chatwoot"><img src="https://agentmods.dev/badge/skills/felipefontoura/bento/chatwoot.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 5.1 | $0.00196 | $0.01455 |
| Opus 5 | $0.00098 | $0.00727 |
| Sonnet 5 | $0.00039 | $0.00291 |
| Haiku 4.5 | $0.00020 | $0.00145 |
Grade A, and why
chatwoot scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You operate the Application API of a Chatwoot stack already deployed by bento. This is day-2 work: you query and manage conversations, contacts, inboxes, and agents. For the exact endpoint paths, parameters, and request bodies, go to the official docs (linked at the bottom) — they are the source of truth. Your job is to know how to approach it, not to memorize the reference.
Golden rule — mutate via the API, never the DB. Raw
INSERT/UPDATEon Postgres bypasses Chatwoot's event pipeline (ActionCable, webhooks, Sidekiq) and leaves the UI in a broken state.
When to invoke
- "reply to / message a customer"
- "list open / unassigned / snoozed conversations"
- "create a new conversation / ticket"
- "assign this conversation to an agent or team"
- "resolve / reopen / snooze a conversation"
- "create / search / list contacts"
- "list inboxes"
- "add a private note to a conversation"
For getting Chatwoot running use /bento:deploy.
Discover the instance — don't hardcode
ssh "$user@$host" "jq -r '.envs.chatwoot.CHATWOOT_HOST' \$HOME/.config/bento/state.json"
Base URL is https://<CHATWOOT_HOST>. The two containers follow bento's swarm
naming convention: chatwoot_chatwoot_web.1.* (Rails) and
chatwoot_chatwoot_sidekiq.1.* (background worker).
Finding account_id
Every Application API route is account-scoped: /api/v1/accounts/{account_id}/...
Read it from the browser URL after login (/app/accounts/**1**/dashboard), or
confirm via Rails runner:
ssh "$user@$host" "docker exec \$(docker ps -qf name=chatwoot_chatwoot_web) \
bundle exec rails runner 'puts Account.pluck(:id, :name).inspect'"
Auth model — the non-obvious parts
All three API surfaces use an api_access_token header — not
Authorization: Bearer.
- Application API (
/api/v1/accounts/...) — day-to-day inbox work. Two token flavors: user token (Profile → Access Token; carries that agent's permissions) and agent bot token (Settings → Integrations → Agent Bots; system identity, broader scope — use for automation). - Platform API (
/api/v1/platform/...) — super-admin provisioning (create accounts, users). Token from Super Admin console →https://<CHATWOOT_HOST>/super_admin/platform_apps. - Client API (
/public/api/v1/inboxes/...) — in-widget visitor flows. Out of scope 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.
- 8d ago First seen · 121 lines · 196 tokens per session scan A 4eef24f8ba58
chatwoot is a skill published in the GitHub repository felipefontoura/bento (20 stars, last pushed 1mo ago), licensed MIT. It adds 196 tokens to every session and 1,455 once invoked, about $0.0010 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
intent-recognition
Classifies automation requests using two decisions: anchor (which primitive owns the top-level control flow — workflow-anchored, agent-anchored, needs-clarification, or out-of-scope) and embedsother (whether the other primitive appears embedded inside — an agent step inside a workflow, or a workflow invoked as an…
post-build-flow
Handles workflow verification and setup after build-workflow succeeds, or when the message contains workflow-verification-follow-up or workflow-setup-required. Load after direct builds, when verificationReadiness requires action, or on orchestrator verify/setup follow-up turns.
data-table-manager
Load before calling data-tables or parse-file. Use for natural standalone requests like "what data tables do I have?", "show/list my tables", or "what columns are in this table?", and whenever the user asks to list, show, create, inspect, import, seed, query, update, clean up, rename columns in, or delete data tables…
planned-task-runtime
Handles system follow-up turns: planned-task-follow-up (synthesize, replan, build-workflow, checkpoint), background-task-completed, running-tasks context, and create-tasks silence rules. Load whenever any of these tags appear or after calling create-tasks.
planning
ONLY for coordinated multi-artifact work: multiple workflows with dependencies, shared data-table schema/migration across tasks, or the user explicitly asked to review a plan first. Load create-tasks via loadtool before calling it (search "create tasks" if not visible). Do NOT use for new one-off workflows…
n8n-cli
Use the n8n CLI to manage workflows, credentials, executions, and more on an n8n instance. Use when the user asks to interact with n8n, automate workflows, manage credentials, or operate their instance from the command line.