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 agentmods add skills/tomzx/agents/create-messagenpx skills add tomzx/agents --skill create-messagegit clone --depth 1 https://github.com/tomzx/agentsWhat 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 | $0.00027 | $0.00907 |
| Opus 5 | $0.00014 | $0.00453 |
| Sonnet 5 | $0.00005 | $0.00181 |
| Haiku 4.5 | $0.00003 | $0.00091 |
Grade A, and why
create-message 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.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write Message
Takes a draft message and improves it by removing negative tone, reformulating with positive language, and appending actionable suggestions where appropriate.
Prerequisites
- Draft message: The message the user wants to send (provided inline or in a file)
- Recipient (optional): Who the message is for (e.g., "a colleague", "a manager", "a client"), used to calibrate tone
- Context (optional): Any background that helps understand the intent (e.g., "they missed a deadline", "I want to decline a meeting")
Steps
- Read the draft message carefully and identify the core intent.
- Scan for negative tone markers: passive-aggression, blame, criticism without constructive framing, defensiveness, dismissiveness, or vague complaints.
- Reformulate each negative passage using positive language that preserves the original intent.
- Identify any places where actionable suggestions would strengthen the message, and add them.
- Review the revised message for tone consistency, clarity, and brevity.
Tone Rewrite Rules
Remove:
- Blame language ("you failed to", "you didn't", "you never")
- Passive-aggressive framing ("as I'm sure you're aware", "per my last email")
- Vague complaints ("this isn't good enough", "this needs to be better")
- Defensiveness ("I was just trying to", "that's not what I meant")
- Dismissive language ("whatever you think", "it doesn't matter to me")
- Sarcasm or backhanded compliments
Replace with:
- Ownership language ("I'd like us to", "we could", "I suggest")
- Specific, observable descriptions ("the report arrived on Friday, past the Wednesday deadline" instead of "you were late again")
- Constructive framing ("here's what would help", "moving forward, I'd recommend")
- Direct requests ("could you", "would it be possible to")
- Collaborative tone ("let's", "how about we")
Actionable Suggestions
Add concrete suggestions when the message:
- Requests a change in behavior (suggest what specifically to do instead)
- Reports a problem (suggest one or more solutions)
- Sets expectations (suggest clear next steps with timelines)
- Expresses disagreement (suggest an alternative approach)
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.
- 2d ago First seen · 91 lines · 27 tokens per session scan A 537fdd6d7103
create-message is a skill published in the GitHub repository tomzx/agents (5 stars, last pushed 4d ago), licensed MIT. It adds 27 tokens to every session and 907 once invoked, about $0.0001 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.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…