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 nimadorostkar/Claude-Skills-collection --skill internal-commsgit clone --depth 1 https://github.com/nimadorostkar/Claude-Skills-collectionWrote 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/nimadorostkar/claude-skills-collection/internal-comms)<a href="https://agentmods.dev/skills/nimadorostkar/claude-skills-collection/internal-comms"><img src="https://agentmods.dev/badge/skills/nimadorostkar/claude-skills-collection/internal-comms/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/nimadorostkar/claude-skills-collection/internal-comms"><img src="https://agentmods.dev/badge/skills/nimadorostkar/claude-skills-collection/internal-comms.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00037 | $0.01135 |
| Opus 5 | $0.00018 | $0.00567 |
| Sonnet 5 | $0.00007 | $0.00227 |
| Haiku 4.5 | $0.00004 | $0.00113 |
Grade A, and why
internal-comms 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 9d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Internal Communications
Purpose
Write internal messages that get read and acted on. The default internal announcement buries its point in paragraph four, and most readers stop at paragraph one.
When to Use
- Announcing a change, a launch, or an incident.
- Writing a status update or a project summary.
- A memo proposing something.
- Any message where you need people to know or do something.
Capabilities
- Leading with the conclusion.
- Matching length and format to the channel and audience.
- Structuring an announcement so that skimming works.
- Writing an ask that is actually actionable.
Inputs
- What the reader needs to know or do.
- Who they are and how much context they have.
- The channel: a chat message, an email, a document.
Outputs
- A message whose point is in the first sentence.
- Structure that survives skimming.
- A clear, singular ask.
Workflow
- Write the conclusion first — What is the one thing the reader must take away? That is the first sentence. Everything after it is support.
- State the ask explicitly — What must the reader do, and by when? A message with an implied ask gets an implied response, which is none.
- Structure for skimming — Bold the key sentence. Use a heading if it is long. Most readers skim; write for that rather than against it.
- Cut the preamble — "As you may know, over the past several quarters the team has been working on..." Delete it. Start at the point.
- Match the length to the channel — A chat message is three sentences. An email is a screen. A memo is a document that people read once, carefully.
- Say what happens if they do nothing — Most readers' real question is whether this affects them.
Best Practices
- The most common failure is burying the point. If the reader has to reach paragraph three to find out whether this affects them, most of them will not.
- One ask per message. Two asks means one gets done, and it will not be the one you cared about.
- "By Friday" is a deadline. "Soon" is not, and it will not be met.
- Length is a cost you impose on every reader, multiplied by the number of readers. A 600-word update sent to 50 people costs several hours of collective attention.
- Anticipate the question the reader will have. If your announcement will produce twelve replies asking the same thing, answer it in the announcement.
- Write for the person who skims. If the bolded sentences alone convey the message, it works.
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.
- 9d ago First seen · 112 lines · 37 tokens per session scan A ec8aa9c41605
internal-comms is a skill published in the GitHub repository nimadorostkar/Claude-Skills-collection (26 stars, last pushed 25d ago), licensed MIT. It adds 37 tokens to every session and 1,135 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
syndic
Gère un parc de copropriétés en France avec vue portfolio consolidée. Couvre administration, comptabilité (décret 2005, plan comptable copro, 5 annexes), assemblées générales (convocation, PV, notification), appels de fonds, travaux, fournisseurs, recouvrement d'impayés et transition de syndic. Maîtrise les majorités…
implement-improvements
Validate improvements from .turbo/improvements.md, recommend a working set tailored to what's in the backlog, and run one lane: direct fixes, investigation, or planned work. One lane per session. Use when the user asks to "implement improvements", "work on improvements", "address improvements", "process improvement…
note-improvement
Capture an out-of-scope improvement opportunity so it doesn't get lost. Use when the user asks to "note improvement", "save improvement", "track this for later", "remember this improvement", "note this idea", "log improvement", "backlog this", or "park this idea". Also invoke proactively when noticing something…
create-issue
Create a GitHub issue with a drafted title and body. Use when the user asks to "create an issue", "file an issue", "open an issue", "submit an issue", "report a bug", "file a bug report", "file a feature request", or "file a design proposal".
pick-next-issue
Fetch and rank open GitHub issues by community engagement, present the top 3 candidates, and plan implementation for the selected issue. Use when the user asks to "pick next issue", "next issue", "which issue should I work on", "top issues", "most popular issues", "prioritize issues", or "what should I work on next".
split-and-ship
Execute an approved split plan, shipping each change group separately as its own branch and PR or as sequential commits on the current branch. Use when the user asks to "split and ship", "ship the split plan", "create separate PRs", or "split changes into branches".