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 jonZlotnik/how-to-agent --skill rule-of-silencegit clone --depth 1 https://github.com/jonZlotnik/how-to-agentWrote 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/jonzlotnik/how-to-agent/rule-of-silence)<a href="https://agentmods.dev/skills/jonzlotnik/how-to-agent/rule-of-silence"><img src="https://agentmods.dev/badge/skills/jonzlotnik/how-to-agent/rule-of-silence/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/jonzlotnik/how-to-agent/rule-of-silence"><img src="https://agentmods.dev/badge/skills/jonzlotnik/how-to-agent/rule-of-silence.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 | $0.00052 | $0.00565 |
| Opus 5 | $0.00026 | $0.00282 |
| Sonnet 5 | $0.00010 | $0.00113 |
| Haiku 4.5 | $0.00005 | $0.00056 |
Grade A, and why
rule-of-silence 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 12d 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rule of Silence
When a program has nothing surprising to say, it should say nothing. Useful information should flow downstream; ceremony, banners, and self-congratulation should not. Silence is honest: the absence of output is a signal that nothing went wrong.
When to use
- Adding logs or progress output to a tool that may be scripted
- A CLI prints an "Operation completed successfully." banner alongside its real output
- A library wraps every call site with an "Entering function X" log
- Output includes ANSI color or table formatting that other tools will have to undo
Protocol
- Distinguish output from chatter. Output is the answer: data the caller asked for. Chatter is everything else. Send chatter to stderr (or a log file), not stdout.
- On success, default to silent. Print only what was asked for. Empty output on success is a feature.
- Make chatter opt-in.
-v/--verbose/RUST_LOG=…for progress. Quiet stays the default. - On failure, be loud and specific — stderr, non-zero exit, a real error message ([[crash-early]]). The contrast with the quiet success path is what makes failure detectable.
- Never decorate piped output. No headers, no totals, no "Found N results" lines mixed into the data stream. If you want a summary, make it a separate command or a
--summaryflag.
Red flags (rationalizations to reject)
- "Users like to see that it's working." — Add a
--progressflag for humans. Don't impose it on every script that pipes through you. - "Silence is scary." — Scarier still: a "success" line that fired even though the real work silently failed two layers down.
- "It's just one log line." — Multiplied by every tool in the pipeline, it's a wall of noise that hides the actual signal.
Composes with
- [[rule-of-composition]] — pipelines depend on clean streams; chatter on stdout breaks them.
- [[crash-early]] — silence on success only works because failure is loud and specific.
- [[rule-of-least-surprise]] — silent success matches the convention every Unix tool already follows.
- [[prove-dont-assume]] — assertions can fail loudly without polluting the stdout of the happy path.
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.
- 12d ago First seen · 37 lines · 52 tokens per session scan A 1e71eb77d91d
rule-of-silence is a skill published in the GitHub repository jonZlotnik/how-to-agent (2 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 565 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…