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/danielrmay/claudity/messagenpx skills add danielrmay/claudity --skill messagegit clone --depth 1 https://github.com/danielrmay/claudityWhat 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 | $0.00010 | $0.02086 |
| Opus 5 | $0.00005 | $0.01043 |
| Sonnet 5 | $0.00002 | $0.00417 |
| Haiku 4.5 | $0.00001 | $0.00209 |
Grade A, and why
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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This works best when the problem and solution documents have real content — if they're still templates, say so and route through Claudity's start skill first. If the user named an audience or messaging focus when invoking this skill, honor it; follow the guide below from the beginning. The summary is not recorded until it was either written with the write_protocol_document tool or recorded via the --record script step near the end of this guide — a native file write alone does not record state.
Message Clarification
Build the narrative that explains what this project is and why anyone should care — starting with the general story and optionally developing audience-specific versions.
Overview
Good messaging isn't marketing — it's a thinking tool. When you can articulate what the project is and why it matters in a way that resonates, it means you actually understand what you're building. When you can't, that's a signal that something in the design needs work. If you can't tell a good story about the system, you don't have a good system.
This process produces two artifacts:
summary.md(required) — the project introduction. A name, a short narrative that explains the what and the why, written like you're talking to someone about something you care about. This is always the first thing someone reads.messaging.md(optional) — audience-specific narratives for projects that need to be explained to different groups. Each audience gets a version of the story that speaks to their concerns and priorities.
This is a conversational process. You're not filling in templates — you're helping the user find the words that feel true and land well.
When to Use This Process
Run this when:
- The problem and solution are solid enough to tell a story about (both should exist, even if rough)
summary.mdis stale, reads like a mechanical spec, or doesn't exist yet- The user is preparing to explain the project to people (stakeholders, investors, users, skeptics)
- The user is stuck and can't articulate what they're building — working on the narrative often unsticks the design itself
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 · 171 lines · 10 tokens per session scan A 9f8c6a0a037c
message is a skill published in the GitHub repository danielrmay/claudity (5 stars, last pushed 2mo ago), licensed MIT. It adds 10 tokens to every session and 2,086 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…