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 fullymiddleaged/Clawness --skill messaginggit clone --depth 1 https://github.com/fullymiddleaged/ClawnessWrote 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/fullymiddleaged/clawness/messaging)<a href="https://agentmods.dev/skills/fullymiddleaged/clawness/messaging"><img src="https://agentmods.dev/badge/skills/fullymiddleaged/clawness/messaging/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/fullymiddleaged/clawness/messaging"><img src="https://agentmods.dev/badge/skills/fullymiddleaged/clawness/messaging.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00135 | $0.01231 |
| Opus 5.5 | $0.00054 | $0.00492 |
| Sonnet 5.5 | $0.00027 | $0.00246 |
| Haiku 4.5 | $0.00014 | $0.00123 |
Grade A, and why
messaging 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 13d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Customer-as-hero messaging
Most product copy describes the product: its features, its stack, its history. People skim past that, because they're looking for their own problem. This skill rewrites copy as a short story where the customer is the hero, the product is the guide that helps them win, and every screen answers "what's in it for me?" within a few seconds.
Say this before you start. Copy changes are visible to every user. Whether the user
typed /clawness:messaging or you reached for this skill yourself: scan, draft the
brief, and stop for approval before editing any copy.
Argument
/clawness:messaging [surface]. The surface is what to work on: landing, onboarding,
pricing, empty-states, a route, or a file. With no argument, find the
highest-traffic surface (usually the landing page or first-run screen) and propose
starting there.
The brief (seven parts, one line each)
| Part | Question it answers | Bad sign |
|---|---|---|
| Hero | Who is the customer, and the ONE thing they want here? | "Everyone"; several wants |
| Problem | What's in their way: the external obstacle, how it makes them feel, why it's unfair | Only the external problem; nobody buys a fix for a feeling they weren't shown |
| Guide | Why trust us: empathy ("we get it") plus proof (numbers, logos, reviews) | Bragging with no empathy, or empathy with no proof |
| Plan | Three or fewer steps from where they are to using it | A feature list instead of steps |
| Call to action | One direct CTA ("Start free") plus one low-commitment one (a guide, a demo) | Several competing primary buttons; "Learn more" as the only CTA |
| Stakes | What it costs them to do nothing | Fear-mongering, or nothing at all |
| Success | Their life after: concrete, visual, specific | "Unlock your potential" |
The brief is the deliverable that matters. Copy is just the brief applied to a screen.
Steps
1. Scan the existing copy
Find where copy lives: route files and components for hero sections and CTAs, i18n
message catalogs (the best source: every user-facing string in one place), CMS or
Markdown content, <title>/meta descriptions, app-store listings. Read the README and
any docs for who the product is for. Collect the current headline, subhead, primary
CTA, and section headings for the surface.
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.
- 13d ago First seen · 100 lines · 135 tokens per session scan A ef15883f2bca
messaging is a skill published in the GitHub repository fullymiddleaged/Clawness (5 stars, last pushed 13d ago), licensed MIT. It adds 135 tokens to every session and 1,231 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-10-04.
Other skills, from other repositories
linked-intent-dev
Guide for linked-intent development (LID). Consult for ALL code changes. Walks changes through a mode-aware six-phase workflow (HLD → LLD → EARS → intent-narrowing edge audit → tests-first → code) with mandatory stops between each phase. Bugs walk the arrow like any other change — no short-circuit. Enforces cascade…
update-lid
Configure or reconcile a project for linked-intent development (LID). Dispatches on project state — fresh bootstrap, append directives to an existing agent-instructions file (AGENTS.md or CLAUDE.md), add missing mode marker, reconcile convention drift, or run mode transitions. Invoked as /update-lid. For fresh…
lid-coach
Review a project's current linked-intent-development (LID) usage against LID's own principles and produce a prioritized report of recommendations for getting more out of the methodology. Invoke when the user runs /lid-coach, asks for a LID review, asks how they could use LID better, wants feedback on their LID setup…
arrow-maintenance
Navigation and audit overlay for linked-intent development. Use when working with docs/arrows/ — orienting via index.yaml, auditing spec-to-code coherence, detecting reverse orphans and drift, splitting/merging/renaming/re-parenting segments. Dual-mode: ambient guidance when the overlay is present…
map-codebase
Bootstrap LID in an existing (brownfield) codebase. Deep-reads every file in the declared scope, offers lens-based clustering options, generates skeleton LLDs/HLD/EARS bottom-up, then creates arrow docs and prompts the user to flesh out the skeletons. Token-intensive by design. Use when asked to map a codebase…
review-depth
Experimental declared review depth for linked-intent development. Use when a LID project's instruction file declares a review depth in prose (e.g. "Review depth - I review through LLD; below that, consolidate to one review") or the user asks to batch phase reviews, consolidate stops, or let go below a phase depth.…