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 yogasw/wick --skill wick-silent-repliesgit clone --depth 1 https://github.com/yogasw/wickWrote 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/yogasw/wick/wick-silent-replies)<a href="https://agentmods.dev/skills/yogasw/wick/wick-silent-replies"><img src="https://agentmods.dev/badge/skills/yogasw/wick/wick-silent-replies/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/yogasw/wick/wick-silent-replies"><img src="https://agentmods.dev/badge/skills/yogasw/wick/wick-silent-replies.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 | $0.00073 | $0.00671 |
| Opus 5 | $0.00036 | $0.00336 |
| Sonnet 5 | $0.00015 | $0.00134 |
| Haiku 4.5 | $0.00007 | $0.00067 |
Grade A, and why
wick-silent-replies 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 8d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Silent replies ([silent])
If nobody needs to read this turn's reply, make the literal marker [silent]
the very first thing you output, then continue on the same line:
[silent] run 3/5: 200 OK, nothing new
That line is the entire mechanism — no tool call, no flag. Reading this skill does nothing by itself; the marker must appear in the text you emit.
Effect: the reply reaches no channel (Slack, Telegram, …) and raises no push notification. It still records to the conversation — the web session shows it with a muted-bell chip, marker stripped — so the trace survives.
The marker is a prefix test
Checked against the start of the whole reply. Case ignored, leading whitespace and newlines tolerated. Anything else in front breaks it:
| Reply starts with | Result |
|---|---|
[silent] … or [SILENT] … |
silent ✅ |
Checked the endpoint. [silent] |
❌ marker mid-text |
| any opener, marker on a later line | ❌ whole turn hits Slack — with [silent] leaked into it |
**[silent]** or `[silent]` |
❌ decorated ≠ literal |
The opener case is the one that actually happens: even "Okay, checking…"
before the marker defeats it. No preamble, no bold, no backticks — plain
[silent], first characters.
Go silent when
- a monitor/poll round found nothing new
- a scheduled run is mid-sequence, not the final one
- ticket bookkeeping with nothing to decide — the sweeper's follow-up prompt asks for exactly this
- an intermediate step of work you were told to just do
Keep the text after the marker informative: [silent] run 3/5: 200 OK is a
useful trace, [silent] ok is not.
Reply normally when
- the watched thing changed — succeeded, failed, crossed a threshold
- you are blocked, or need a decision, approval, or credential
- it is the final summary of a loop, schedule, or chain
- anything with a cost, a risk, or a surprise in it
- the user asked a direct question — a person waiting on you always gets a visible answer, even a short one
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.
- 8d ago First seen · 66 lines · 73 tokens per session scan A 167617dac6a1
wick-silent-replies is a skill published in the GitHub repository yogasw/wick (5 stars, last pushed yesterday), licensed MIT. It adds 73 tokens to every session and 671 once invoked, about $0.0004 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
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
omh-code-review
This is a Hermes-native code-review workflow skill.
redteam-web-detail-pack
Routing and boundary guidance for authorized general web application security testing. Use as a web testing router when the attack surface should be dispatched to more specific web vulnerability skills.
android-pentest
A guide for authorized security testing of Android apps, covering APK inspection, runtime testing, traffic capture, code review, and function hooking. An APK is the installable package used by an Android app.
workflow-builder
Load before calling build-workflow. Default path for all single-workflow work: new one-off workflows, existing-workflow edits, verification repairs, and workflow-local data tables. Write or edit a workspace source file, run workflow-sdk validate via workspaceexecutecommand, then call build-workflow with filePath. When…
jikegongyuan-perspective
A writing guide based on GeekPark, a Chinese technology publication and entrepreneur community focused on AI, products, startups, and innovation.