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 tomzx/agents --skill communication-guidelinesgit clone --depth 1 https://github.com/tomzx/agentsWrote 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/tomzx/agents/communication-guidelines)<a href="https://agentmods.dev/skills/tomzx/agents/communication-guidelines"><img src="https://agentmods.dev/badge/skills/tomzx/agents/communication-guidelines/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/tomzx/agents/communication-guidelines"><img src="https://agentmods.dev/badge/skills/tomzx/agents/communication-guidelines.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 | $0.00070 | $0.01339 |
| Opus 5.5 | $0.00028 | $0.00536 |
| Sonnet 5.5 | $0.00014 | $0.00268 |
| Haiku 4.5 | $0.00007 | $0.00134 |
Grade A, and why
communication-guidelines 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 22d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Communication Guidelines
Shared baseline for every piece of text the agent writes on the user's behalf, whether the agent posts it or returns it for the user to send. Other skills reference this file instead of restating concision and tone rules. This is a reference, not a workflow: no command to run and no artifact to produce.
When to use
- Any skill that composes text a human will read on GitHub, Slack, or email.
- Loaded by name from other skills, for example "apply
skills/communication-guidelines/SKILL.mdbefore composing the body". - Loaded directly when the user asks to post a comment, reply on a PR or issue, write a PR or issue description, or draft a message.
Core principles
- Be concise.
- Use plain language: short, direct sentences in the active voice, with common words over jargon and buzzwords.
- Write literally, with no metaphors, idioms, or other figurative language the reader must decode.
- Lead with the point: the ask, finding, decision, or answer is the first sentence.
- Do not use em-dashes, use commas or parentheses instead.
- One sentence per line.
- Write the shortest form that carries the signal, then delete every sentence that does not change what the reader knows or does.
- One idea per message, comment, or thread reply.
- Do not restate what the code, diff, linked issue, or the comment being replied to already says.
- Be concrete: name the file, line, symbol, and the specific change.
- Give the reader the reason they need to act, not the reasoning trail that produced it.
- Prefer a link to the artifact (issue, ADR, spec, dashboard) over re-explaining its content.
- Mark severity and optionality so the reader can prioritize, using MUST/SHOULD/MAY or an explicit "nit".
- Assume competence and criticize the work, not the person.
- For tone rewrites, use
create-message. - For the full catalog of patterns to remove (AI-favored words, filler, hedging, punctuation, and artificial patterns), apply
references/writing-rules.md.
What ships with it
1 file 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.
- 22d ago Changed · +4 lines 68d46af0d7b3
- 23d ago Changed · +4 lines 5103a7ac794f
- 25d ago Changed 1ec22bfc96c3
- 27d ago Changed · +1 lines 752b530de6eb
- 28d ago First seen · 107 lines · 70 tokens per session scan A 6baf466eed7b
communication-guidelines is a skill published in the GitHub repository tomzx/agents (13 stars, last pushed yesterday), licensed MIT. It adds 70 tokens to every session and 1,339 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 2026-10-01.
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…
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.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…