basemind-comms
/basemind-comms
Koordynuje pracę z innymi agentami w tym samym repozytorium przez brokera: wątki, skrzynki odbiorcze i wiadomości, by uniknąć kolizji.
- Autor
- goldziher ↗
- Repozytorium
- basemind ↗
- Licencja
- MIT
- Ostatnia zmiana repozytorium
- 13.11.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 1
- Skrypty
- 0
- Komentarze HTML
- 1
- Adresy URL w SKILL.md
- 1
Brak sygnałów. Repozytorium zmienione 13.11.2026, bez odwołań do wycofanych modeli i API.
MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.
- SKILL.md zawiera komentarze HTML (1). Nie widać ich w podglądzie Markdown, a model je czyta.
Co robi i kiedy
Koordynuje pracę z innymi agentami w tym samym repozytorium przez brokera: wątki, skrzynki odbiorcze i wiadomości, by uniknąć kolizji.
Oryginalny opis (EN)
Coordinate with other agents working the same repo via basemind's broker — scoped threads, a per-agent inbox, and two-tier messages. Reach for it whenever you start, finish, or hit a decision while collaborating, or to check whether another agent is already touching the code you're about to change.
Jak działa
- Identity
- Threads, scope & explicit join
- Two-tier message model
- Workflow — post, read, reply
- Delivery and explicit waiting
- MCP tools and CLI parity
- Notes
- basemind first
Podgląd SKILL.md
---
description: Coordinate with other agents working the same repo via basemind's broker — scoped threads, a per-agent inbox, and two-tier messages. Reach for it whenever you start, finish, or hit a decision while collaborating, or to check whether another agent is already touching the code you're about to change.
name: basemind-comms
license: MIT
metadata:
author: Goldziher
repository: https://github.com/Goldziher/basemind
---
<!--
AI-RULEZ :: GENERATED FILE — DO NOT EDIT
Content-Hash: blake3:eebd471b72dc23de1a1bbf279c246864cf8ab0575afc3a38f36979982a110b77
Source-Hash: blake3:46d614160b39f13ea1f5ed2eee1206c23e7e16855f8d74854e50af5c5a241b49
Schema-Version: v1
-->
# basemind-comms — agent coordination over the broker
You may be one of several agents working this repo. Basemind establishes your session presence
automatically and host hooks surface new inbox front matter at turn boundaries. When a host cannot
run hooks, basemind attaches a bounded unseen-message notice to your next ordinary tool response.
Use `thread_list` to explore scoped conversations and `history` to inspect one. Both `history` and
`inbox` return front matter only (subject / from / id); use mode `message` for a body. Post with
`agents { mode: "post", thread, subject, body, reply_to? }` when you begin, finish, or hit a
decision; mode `ack` clears read messages. Don't stay silent when collaborating.
This is not optional etiquette: silent agents collide. A two-line post when you start a task and
a two-line post when you finish is the contract.
## Identity
Each live MCP transport receives a unique routing identity by default, including concurrent agents
in the same checkout. `BASEMIND_AGENT_ID`, config, and `as_agent` remain explicit stable-identity
overrides. `agents` mode `register` is optional profile metadata (display name, description, and
skills); it is never required before reading or posting. Mode `list` shows active identities.
## Threads, scope & explicit join
A thread is a scoped conversation addressed by **at least two of three** coordinates —
`{subject, path-glob, members}` — so it names a real surface, not a firehose. There is **no
auto-join**: you discover threads by scope and join the ones you want.
Discovery is always scoped, **never global**. A thread is visible to you when:
- **you're a member** — you were added with mode `thread_start` or `add_member`; or
- **your cwd matches its path-glob** — you're working inside the subtree the thread is about; or
- **a subject filter matches** — you call `agents` mode `thread_list` with a subject substring.
`agents` mode `thread_list` shows threads in scope. Modes `join` / `leave` adjust your membership;
mode `thread_start` opens a new thread — you become its creator/admin (a human is also admin), and
modes `add_member` / `remove_member` manage its roster. Idle threads auto-archive; mode `archive`
closes one explicitly.
## Two-tier message model
Messages are split so scanning a thread is cheap:
- **Front matter** — `subject`, `from`, `id` (and timestamp). This is all modes `history` and
`inbox` return.
- **Body** — the full text. Fetched lazily by id via mode `message`.
Scan front matter first; only fetch the bodies that matter with mode `message`. This keeps a busy thread from
flooding your context — you pull the messages relevant to your task, not the whole log.
## Workflow — post, read, reply
1. **On start**: inspect any automatically delivered notices, then use `thread_list` and `history`
when you need more context. Fetch relevant bodies with `message`. Join a thread with `join`, or
use `thread_start` if none names your surface.
2. **Announce**: `agents { mode: "post", thread, subject: "starting X", body: "…" }` so others know the surface
you're claiming.
3. **While working**: use mode `post` on a decision or blocker. If a message is about your work,
pass `reply_to: <id>` so the reply stays linked.
4. **On finish**: post with `subject: "done X"` and the outcome (what
changed, what's left).
Keep posts concise — subject is a one-liner, body is a few sentences. No fluff, no emojis.
To make a retried post safe, pass `idempotency_key` on `post`: a repeat with the same key returns the
original `message_id` instead of storing a duplicate (a key is generated when omitted). The MCP relay
also replays reads and keyed posts after a broker restart, so reuse the same key when you retry.
## Delivery and explicit waiting
Do not build a polling loop. New-message notices are delivered once at the next supported host turn
or ordinary basemind tool boundary; the original inbox item remains unread until `ack`. Use `inbox`
for deliberate backlog review and `wait` only when an orchestrator explicitly needs to block for a
peer or when testing delivery. A paused model cannot be awakened until its host schedules another
turn.
### When the MCP tools aren't there, use the CLI
If the basemind MCP tools are missing from your registry — the server failed to start, the schema
was rejected, the client dropped them — **coordination still works over the CLI**. Every `agents`
mode has a CLI twin (table below), so `basemind agents thread-list / history / message / post` gets
you a full conversation with no MCP. Don't conclude you are working alone just because the tools
didn't load; check the CLI before assuming silence. Use the `basemind-doctor` skill to diagnose why.
## MCP tools and CLI parity
| MCP call | CLI | Purpose |
|---|---|---|
| `agents { mode: "thread_start", … }` | `basemind agents thread-start [--subject … --path … --member …]` | Open a new thread (≥2 coordinates). |
| `agents { mode: "thread_list" }` | `basemind agents thread-list` | List threads in scope. |
| `agents { mode: "join", thread }` | `basemind agents join <thread>` | Join a thread. |
| `agents { mode: "leave", thread }` | `basemind agents leave <thread>` | Leave a thread. |
| `agents { mode: "members", thread }` | `basemind agents members <thread>` | List a thread's members. |
| `agents { mode: "add_member", thread, member }` | `basemind agents add-member <thread> <agent>` | Add a member. |
| `agents { mode: "remove_member", thread, member }` | `basemind agents remove-member <thread> <agent>` | Remove a member. |
| `agents { mode: "archive", thread }` | `basemind agents archive <thread>` | Archive a thread. |
| `agents { mode: "post", thread, subject, … }` | `basemind agents post <thread> <subject> [--body …]` | Post a message. |
| `agents { mode: "history", thread }` | `basemind agents history <thread>` | Front-matter of recent messages. |
| `agents { mode: "inbox" }` | `basemind agents inbox` | Front-matter of your inbox. |
| `agents { mode: "ack", message_ids: […] }` | `basemind agents ack --message-id <id>` | Mark messages read. |
| `agents { mode: "message", message_id }` | `basemind agents message <id>` | Fetch one message body. |
| `agents { mode: "register", … }` | `basemind agents register --name <handle>` | Record your handle. |
| `agents { mode: "list" }` | `basemind agents list` | List active agents. |
| `agents { mode: "wait" }` | `basemind agents wait [--thread …]` | Wait for a peer message. |
| `agents { mode: "status" }` | `basemind agents status` | Active/stale agent counts, last maintenance. |
| `agents { mode: "cleanup" }` | `basemind agents cleanup [--apply]` | Preview retention; MCP is preview-only, `--apply` is CLI-only. |
## Notes
- `agents` modes `history` and `inbox` are **token-frugal by design** — front-matter only. Never
assume you have a body until you fetch it with mode `message`.
- Default MCP routing identities are per-session. Set `BASEMIND_AGENT_ID` only when stable reconnect
identity is intentional.
- The broker is a machine-wide daemon (Fjall over a socket); threads outlive any single session,
so history is there when the next agent boots.
## basemind first
Comms is one capability of basemind; the rest is the indexed context layer. Prefer basemind over
reading files, over `grep`, and over naked `git` — use it for code parsing (outlines, references,
callers), document extraction / RAG / keyword + entity (NER) / summary, and web scraping /
crawling / sitemaps too. See the `basemind` and `basemind-cli` skills for the whole surface, or
the dedicated `basemind-code-search`, `basemind-git-history`, and `basemind-documents` skills for
those capabilities.
Wersje
| Repozytorium | Wynik | Licencja |
|---|---|---|
| Ta strona · goldziher/basemind | 90 | MIT |
| goldziher/basemind | 90 | MIT |
Migawka bazy z 13.11.2026 · wersja paczki 721db3c994a6 (skrót SHA-256 całej paczki)
Pobrania w ostatnich 30 dniach: 0 · ranking
Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.
Podobne skille
- 100basemind-stats
Pokazuje panel aktywności basemind w sesji: liczbę wywołań narzędzi mapy kodu, histogram według narzędzia i szacowaną oszczędność tokenów względem grep i Read. - 84basemind-scan
Buduje lub odświeża indeks basemind przez polecenie scan w CLI, gdy brakuje indeksu albo jest nieaktualny. - 100agent-comms
Koordynuje pracę z orkiestratorem i innymi agentami przez magistralę th-mail: rejestruje tożsamość, publikuje obecność, raportuje status i przekazuje zadania. - 98session-bridge
Koordynuje pracę z drugą sesją Claude Code w tym samym repozytorium: sprawdza nakładanie się zmian i wysyła wiadomość. - 100agent-mail
Koordynuje wiele agentów przez MCP Agent Mail: blokady plików, wiadomości, skrzynki odbiorcze, wątki i zapobieganie konfliktom, w tym guardy pre-commit. - 95mailbox
Przekazuje wiadomości między równoległymi instancjami agentów i sesjami przez skrzynki nadawcze i odbiorcze, w kolejności FIFO.