Borrowing it
Nothing to install: this file belongs to vvedantb/eva. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vvedantb/eva/main/.claude/skills/eva-tweet/SKILL.mdgit clone --depth 1 https://github.com/vvedantb/evaWrote 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/vvedantb/eva/eva-tweet)<a href="https://agentmods.dev/skills/vvedantb/eva/eva-tweet"><img src="https://agentmods.dev/badge/skills/vvedantb/eva/eva-tweet.svg" alt="Measured on agentmods" 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 | $0.00085 | $0.01553 |
| Opus 5 | $0.00043 | $0.00776 |
| Sonnet 5 | $0.00017 | $0.00311 |
| Haiku 4.5 | $0.00009 | $0.00155 |
Grade A, and why
eva-tweet 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 3d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vedant's tweet voice
These are dev-tool shipping posts. The reader is another engineer scrolling fast. The tweet's job is to state what now exists and what it can do — nothing else. No selling, no story, no thread of context.
The whole style is one idea: capability lists do the persuading. You never write that something is fast or powerful; you write 83ns update dispatch and let the reader conclude it.
This is a written voice and it is not the same as [[vedant-voice]], which is spoken, warm, and story-shaped (before→now→why). Do not import that structure here. Tweets are flat, clipped, and declarative.
The shape
Almost every post is the same four blocks, separated by blank lines. Blocks 2 and 4 are optional.
1. Hook — what now exists, one line
2. Positioning — what it is, one fragment (no verb needed)
3. Arrow list — 3–5 capabilities, each prefixed →
4. Close — the goal, the payoff, or a fragment triad
Worked example:
Introducing <terminal />
A built-in component for Native SDK
→ Real shell on a PTY
→ Powered by libghostty-vt
→ Selection, scrollback + truecolor
→ Record sessions, replay them offline
Give your software factory or agent orchestrator a terminal
Short posts drop straight to blocks 1–2, or 1 alone:
portless v0.15.3 is out
HTTPS from WSL now just works in Windows browsers
Block 1 — the hook
One line. It names the thing and the fact that it exists now. Pick the opener that matches what actually happened:
Introducing X— a genuinely new product or surfaceNew experiment: X— early, unproven, explicitly a puntNow available: X— a feature landing in something that already shippedX now <verbs>— an existing thing gained a capability ("Native SDK now renders CJK")You can now <do X>— framed from the user's sideX v0.15.3 is out— a version bump
Never We're excited to announce. Never 🚀. Never a question as the hook.
Block 2 — positioning
One fragment, no full sentence needed, no period required. It answers "what is this" for someone who's never heard of it.
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.
- 3d ago First seen · 139 lines · 85 tokens per session scan A 99de43b79d1c
eva-tweet is a skill published in the GitHub repository vvedantb/eva (101 stars, last pushed yesterday), licensed MIT. It adds 85 tokens to every session and 1,553 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
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…