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 uchicago-dsi/ai-sci-skills --skill agentcommgit clone --depth 1 https://github.com/uchicago-dsi/ai-sci-skillsWrote 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/uchicago-dsi/ai-sci-skills/agentcomm)<a href="https://agentmods.dev/skills/uchicago-dsi/ai-sci-skills/agentcomm"><img src="https://agentmods.dev/badge/skills/uchicago-dsi/ai-sci-skills/agentcomm/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/uchicago-dsi/ai-sci-skills/agentcomm"><img src="https://agentmods.dev/badge/skills/uchicago-dsi/ai-sci-skills/agentcomm.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00066 | $0.01923 |
| Opus 5.5 | $0.00026 | $0.00769 |
| Sonnet 5.5 | $0.00013 | $0.00385 |
| Haiku 4.5 | $0.00007 | $0.00192 |
Grade A, and why
agentcomm 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 3d 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentComm
Default To The Mailbox
Default to AgentComm for peer and Claude-worker assignments, replies, and coordination. Do not duplicate the conversation through tmux. Use tmux only for a verified wake-up need, onboarding, or a failed or unavailable mailbox; state the reason and keep a wake-up notice short, pointing to the mailbox.
An unread message alone is not proof of a failed communication channel.
Where It Lives
Install agentcomm user-wide rather than inside a project environment, so the
mailbox survives environment switches and every agent on the machine reaches the
same one. A reference layout: the binary on PATH under ~/.local/bin, the
pinned npm package @yonidavidson/[email protected] under ~/.local/lib/agentcomm,
and messages under ~/.local/share/agentcomm/mailbox.
Keep the mailbox outside Git and outside cache directories. Pin the package version: the roster and read-state semantics below are what that version does.
Bind A Durable Name Once Per Session
Codex agents run agentcomm bind <name> once per session, using their own
durable name.
Claude must run agentcomm register --as <name> as well. Setting
AGENTCOMM_AGENT and passing --as is not the equivalent of bind: mail
sends and the mailbox fills, but the name never joins the roster that
agentcomm agents returns. A peer then sees replies queued to a mailbox
nothing is known to be reading, and reasonably concludes the agent does not
exist. This has already cost one round trip. Register once per session,
before the first send:
export AGENTCOMM_AGENT=mao
agentcomm register --as mao # joins the roster; --as alone does not
agentcomm agents --json | grep mao # confirm, do not assume
Then:
agentcomm send picard "message" --as mao --subject status
agentcomm inbox --json
agentcomm agents --json
inbox consumes and archives under ~/.local/share/agentcomm/mailbox/read/<name>/.
Read it once and the body is gone from the listing; read the archive directly to
recover a message you consumed before acting on it. Consuming is not a claim that
the requested work is done, only that you have seen it.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago Changed · +2 lines 997196df627f
- 1mo ago First seen · 168 lines · 66 tokens per session scan A 9c090f3f689c
agentcomm is a skill published in the GitHub repository uchicago-dsi/ai-sci-skills (20 stars, last pushed 4d ago), licensed MIT. It adds 66 tokens to every session and 1,923 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-23.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.