internal-comms

Guidance for writing clear internal messages such as incident reports, post-mortems, launch announcements, project updates, leadership briefings, and team FAQs. It focuses on helping busy colleagues quickly understand what happened and what they need to do.

In plain words
What is it for?
Use it to write incident updates, post-mortems, launch messages, status reports, all-hands summaries, leadership briefings, and internal FAQs.
Why use it?
It removes ambiguity and unnecessary length from workplace communication. It helps put the main conclusion and any required action where readers will see them.

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/code-saurabh/openskills/internal-comms
Any agent
npx skills add CODE-SAURABH/OpenSkills --skill internal-comms
Clone the repo
git clone --depth 1 https://github.com/CODE-SAURABH/OpenSkills

Made for: Claude Code, Codex.

Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,553 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 $0.00089 $0.02553
Opus 5 $0.00044 $0.01277
Sonnet 5 $0.00018 $0.00511
Haiku 4.5 $0.00009 $0.00255

Measured yesterday against content hash 8dc0eb0fdc61, 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 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 yesterday.

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.

internal-comms/SKILL.md · 309 lines

How it starts

The opening of the file, as written. The whole thing — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Internal Communications

Internal comms fail in two ways: too long (nobody reads them) or too vague (nobody acts on them). The goal is a message that gets read, understood, and acted upon — by the right people, in the right amount of time.

Write for the reader's context, not your own. The reader is busy, has incomplete context, and will skim before they read. Lead with the conclusion.


Internal Comms Principles

  • Lead with the bottom line. The most important thing goes first. Background and rationale come after. Executives and busy engineers read the first paragraph and stop.
  • One message, one action. Every communication has exactly one thing it wants the reader to do: approve, acknowledge, unblock, attend, or stay informed. Name it explicitly.
  • Shorter is always harder to write and easier to read. Spend the extra time to cut.
  • Tone matches urgency and audience. A P0 incident update is clinical and fast. A team launch announcement is warm and energetic. Read the room.
  • Never bury the ask. If you need something from the reader, state it in the first 2 sentences or in a clearly labeled "Action Required" section.
  • Facts over feelings in incident reports. What happened, what broke, what was the impact, what we did, what we're doing to prevent recurrence. No blame. No speculation.

Communication Types

1. Incident Report / Post-Mortem

Use when: a production incident, outage, data issue, or security event occurred and needs to be documented.

Format:

## Incident Report — [Service/Feature] — [Date]

**Severity:** P0 / P1 / P2
**Status:** Resolved / Ongoing / Monitoring
**Duration:** [start time] → [end time] ([X hours Y minutes])
**Impact:** [Who was affected, how many users, what they couldn't do]

---

### Timeline
| Time (UTC) | Event |
|---|---|
| HH:MM | Monitoring alert fired for [metric] |
| HH:MM | On-call engineer paged |
| HH:MM | Root cause identified: [one sentence] |
| HH:MM | Fix deployed to production |
| HH:MM | Service confirmed healthy |

### Root Cause
[One paragraph. What broke, why it broke, what conditions triggered it.]

### Impact
- **Users affected:** [number or percentage]
- **Duration of impact:** [X hours Y minutes]
- **Services affected:** [list]
- **Data loss:** [Yes/No — if yes, describe]

### What We Did
[Ordered list of actions taken during the incident]

### Action Items
| Action | Owner | Due Date | Status |
|---|---|---|---|
| [Prevent recurrence action] | @engineer | YYYY-MM-DD | Open |
| [Monitoring improvement] | @engineer | YYYY-MM-DD | Open |

### What Went Well
- [Something the team handled well]

### What Could Be Improved
- [Process or system gap revealed by this incident]

Read the full file on GitHub · 309 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. yesterday First seen · 309 lines · 89 tokens per session scan A 8dc0eb0fdc61

Subscribe to this mod's changes

internal-comms is a skill published in the GitHub repository CODE-SAURABH/OpenSkills (2 stars, last pushed 1mo ago), licensed MIT. It adds 89 tokens to every session and 2,553 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.