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 agents/mblua/agentscommander/inter-agent-messaginggit clone --depth 1 https://github.com/mblua/AgentsCommanderWhat 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 | $0.00000 | $0.03662 |
| Opus 5 | $0.00000 | $0.01831 |
| Sonnet 5 | $0.00000 | $0.00732 |
| Haiku 4.5 | $0.00000 | $0.00366 |
Grade A, and why
inter-agent-messaging 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 yesterday.
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 — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Inter-agent messaging
For developers building or operating multi-agent workflows. The full file-based protocol AC uses to route messages between agents, with the exact filenames, paths, and send CLI usage.
Why files
Messages between agents are plain markdown files. Files are inspectable with cat, version-controllable with git, and arbitrarily large — PTY truncation never applies because the recipient reads the file from disk, not from a PTY injection.
Every coordination step is a
git diffyou can audit.
File layout
For a room room-<N>-<team>:
room-<N>-<team>/
└── messaging/
├── 20260527-150000-wg1-tech-lead-to-wg1-dev-rust-kickoff.md
├── 20260527-150412-wg1-dev-rust-to-wg1-tech-lead-status.md
└── 20260527-151205-wg1-tech-lead-to-wg1-dev-ts-design-question.md
Filename pattern (the CLI rejects anything else):
YYYYMMDD-HHMMSS-room<N>-<from>-to-room<N>-<to>-<slug>.md
| Field | Rules |
|---|---|
YYYYMMDD-HHMMSS |
UTC timestamp at write time. UTC on a non-UTC host will differ from the local wall clock. |
room<N> |
The room number (sender's). |
<from> / <to> |
Local agent name within the room (e.g. tech-lead, dev-rust). |
<slug> |
Sanitised kebab-case, [a-z0-9-]+, ≤50 characters. |
.md |
Always markdown. |
Collisions (same second + same slug) get a numeric suffix: …-status.1.md, …-status.2.md, up to .99.
The two-step protocol
Sending a message is always two steps:
-
Write the file. Put your message in a new file under the room's
messaging/directory using the filename pattern above. -
Fire
send.agentscommander send \ --token "$AGENTSCOMMANDER_TOKEN" \ --root "$AGENTSCOMMANDER_ROOT" \ --to "<canonical-peer-name>" \ --send "<filename>" \ --mode wake
--send takes the filename only, never a path. The CLI resolves it against <room-root>/messaging/:
# bad — triggers "filename contains path separators or traversal"
agentscommander send ... --send "C:/.../messaging/20260527-150000-wg1-a-to-wg1-b-hi.md"
# good
agentscommander send ... --send "20260527-150000-wg1-a-to-wg1-b-hi.md"
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.
- yesterday First seen · 282 lines · 0 tokens per session scan A 1986e9221d3e
inter-agent-messaging is an agent published in the GitHub repository mblua/AgentsCommander (10 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,662 tokens. 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 agents, from other repositories
engine-implementation-executor
Execute an already-reviewed phase.rs implementation plan surgically. Receives the approved plan + scope, edits files, runs Tilt-first verification, and returns a diff summary with any judgement-call notes. Does NOT plan, does NOT review, does NOT commit. Spawned by the /engine-implementer skill.
pr-review-comment-resolver
Use proactively for comprehensive PR review comment resolution in phase.rs. Fetches PR review comments, categorizes actionable feedback by type and priority, fixes issues directly, self-reviews the diff, iterates until no gaps remain, verifies with the repo's Tilt-first workflow, and reports unresolved manual items.
mtg-rules-auditor
Audits MTG Comprehensive Rules coverage in engine code. Accepts targeted file lists or CR sections for lightweight runs, or does a full codebase sweep. Produces structured reports mapping game logic to CR rule numbers.
parser-gap-finder
Analyzes parser coverage gaps, classifies them by failure reason, and proposes prioritized parser fixes to unlock the most cards with the least code changes. Run with cargo parser-gaps data available.
git-workflow
Hermes CN 的需求与 bug 修复通常同时横跨 Desktop 与 Core 两个仓库。正式动手写代码前，两个仓库都必须先过这道预检，不要直接在 main 上改：.
PROJECT_MAP
Agent "PROJECT_MAP" from zyqzyq/Unfour, covering projectmap.md, top-level directory structure, frontend packages, @unfour/ui (packages/ui) and @unfour/command-client (packages/command-client).