internal-comms-writing

A writing guide for clear internal team communications such as updates, incident notes, FAQs, newsletters, and launch announcements.

In plain words
What is it for?
Use it to draft or prepare internal updates, planning messages, rollout communications, meeting follow-ups, and incident documentation.
Why use it?
It helps turn source information into messages that fit the audience, purpose, tone, and approval requirements while separating facts from assumptions.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/codeinfinity1/stram/internal-comms-writing
Any agent
npx skills add CodeInfinity1/Stram --skill internal-comms-writing
Clone the repo
git clone --depth 1 https://github.com/CodeInfinity1/Stram

Made for: Claude Code, Codex.

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 537 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00033 $0.00537
Opus 5 $0.00016 $0.00269
Sonnet 5 $0.00007 $0.00107
Haiku 4.5 $0.00003 $0.00054

Measured 2d ago against content hash 5202ab3e85db, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

internal-comms-writing 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 2d 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.

skills/communications/internal-comms-writing/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Internal Comms Writing

Purpose

Help the user communicate inside teams with clarity, context, and appropriate tone. This skill adapts internal-communications writing patterns into Stram-native drafting, notes, channel preparation, and approval workflows.

When To Use

Use for team updates, exec summaries, incident notes, rollout announcements, FAQ drafts, policy notes, newsletters, planning messages, and post-meeting communications.

Inputs And Evidence

  • Audience, channel, purpose, deadline, desired tone, and length.
  • Source evidence such as meeting notes, task status, logs, docs, or user bullets.
  • Sensitive details that must be included, excluded, or anonymized.
  • Delivery channel setup and approval state.

Tool Map

  • writing_draft_create
  • writing_draft_inspect
  • read_file
  • write_note
  • memory_write
  • channel_message_prepare
  • voice_response_prepare
  • cognitive_interaction_review
  • message-approval-policy

Workflow

  1. Identify audience and purpose before drafting.
  2. Separate verified facts from assumptions and open questions.
  3. Choose a format: short update, FAQ, incident note, announcement, newsletter, or decision memo.
  4. Draft in a concise, direct style with clear next actions.
  5. Save a durable unsent draft with writing_draft_create when persistence is useful.
  6. Prepare a channel message or note when delivery/persistence is requested.
  7. Use approval gates before external-visible or team-visible posting.

Native Implementation Boundaries

  • Use Stram document, note, channel, and cognition tools.
  • Do not import Anthropic or external reference communication skill code as implementation.
  • Use upstream writing examples only as reference inspiration.

Safety And Approval

  • Do not overstate certainty, blame individuals, or disclose private data.
  • Incident and executive comms should preserve uncertainty and known scope.
  • User approval is required before posting.

Verification

  • Confirm each claim maps to evidence or is clearly framed as a draft assumption.
  • Confirm audience and channel match the user's request.
  • Confirm a prepared message is not described as sent.

Read the full file on GitHub · 73 lines

Changes

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.

  1. 2d ago First seen · 73 lines · 33 tokens per session scan A 5202ab3e85db

Subscribe to this mod's changes

internal-comms-writing is a skill published in the GitHub repository CodeInfinity1/Stram (10 stars, last pushed 22d ago), licensed MIT. It adds 33 tokens to every session and 537 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 2026-08-31.