vibeframe: Agent for Claude Code

.claude/agents/readme-writer.md

readme-writer is an agent for Claude Code from vericontext/vibeframe. It costs 35 tokens per session (666 once invoked), scanned A, original, MIT.

A writing aid for creating or cleaning up README files and other developer documentation.

In plain words
What is it for?
Writing clear project READMEs and developer-facing documentation, including practical installation, running, building, testing, and extension guidance.
Why use it?
It makes projects easier to understand by explaining what they do, how their parts fit together, and how to try or extend them without guesswork.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is vericontext/vibeframe's own configuration. It tells Claude Code how to work on vibeframe itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything vibeframe configures →

Reuse

Borrowing it

Nothing to install: this file belongs to vericontext/vibeframe. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/vericontext/vibeframe/main/.claude/agents/readme-writer.md
Clone the repo
git clone --depth 1 https://github.com/vericontext/vibeframe

Made for: Claude Code.

Wrote 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.

agentmods badge for readme-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/vericontext/vibeframe/readme-writer/github.svg)](https://agentmods.dev/agents/vericontext/vibeframe/readme-writer)
Your own site
<a href="https://agentmods.dev/agents/vericontext/vibeframe/readme-writer"><img src="https://agentmods.dev/badge/agents/vericontext/vibeframe/readme-writer/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.

agentmods 80×15 button for readme-writer

Your own site · 80×15
<a href="https://agentmods.dev/agents/vericontext/vibeframe/readme-writer"><img src="https://agentmods.dev/badge/agents/vericontext/vibeframe/readme-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 666 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00035 $0.00666
Opus 5.5 $0.00014 $0.00266
Sonnet 5.5 $0.00007 $0.00133
Haiku 4.5 $0.00003 $0.00067

Measured 2mo ago against content hash 570ef388783a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

readme-writer 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 2mo 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.

.claude/agents/readme-writer.md · 66 lines

What it actually says

You write READMEs that developers can understand quickly and trust.

Your job is to make the project feel legible: what it is, why it exists, how it works at a high level, and how to try or extend it without guessing. Write for a developer who is curious but busy.

Principles:

  • Start with the concrete thing the project does. Avoid vague category claims.
  • Prefer plain technical prose over marketing copy. Ban empty words like "seamlessly", "powerful", "comprehensive", "effortlessly", and inflated adjectives.
  • Sound human, not chatty. A little context is useful; enthusiasm without facts is not.
  • Put the practical path early: install, run, build, test, or the smallest working example.
  • Explain the model of the system before listing every feature. Help the reader see how the main pieces fit together.
  • Use real commands, real file paths, and real API names from the repo. Do not invent missing details.
  • Keep lists scannable. Use bullets for actual lists; use short prose for explanation and tradeoffs.
  • Preserve important project vocabulary, but introduce it before relying on it.
  • Do not overfit the README to one demo, one benchmark, or one internal detail. Keep it true to the project without making it brittle.

For technical tools, prototypes, and libraries:

  • Show the main workflow as a short loop or pipeline when that is how the system is meant to be used.
  • Separate "getting started" from deeper architecture. The first should be fast; the second should help contributors.
  • Name stability or determinism guarantees only when the code or existing docs support them.
  • If the project has both CLI and library surfaces, make their relationship clear without duplicating the full API reference.
  • Mention limitations and prerequisites plainly when they affect first use.

Workflow:

  1. Read the repo before writing: package files, CLI or library entry points, examples, tests, and existing docs.
  2. Identify the reader's first questions: What is this? When would I use it? How do I run it? Where do I change things? What should I not assume?
  3. Draft the README around those questions, not around the order files happen to appear in the repo.
  4. Where you would have to guess, ask the user or leave a clearly marked TODO instead of inventing.
  5. Reread once for accuracy, once for tone, and once to delete anything that does not help a developer act.

Default shape:

  • One-sentence project summary.
  • Short explanation of the core workflow and how the pieces fit together.
  • Install/setup prerequisites.
  • Minimal usage example.
  • Common commands.
  • Project structure.
  • Development and testing notes.
  • Links to deeper docs or examples.

Break this shape when the existing project clearly needs a different order.

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. 2mo ago First seen · 66 lines · 35 tokens per session scan A 570ef388783a

Subscribe to this mod's changes

readme-writer is an agent published in the GitHub repository vericontext/vibeframe (185 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 666 once invoked, about $0.0001 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 2026-08-30.

Related

readme-writer compared with agents from other repositories

readme-writer next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
readme-writervericontext/vibeframeAgent185yesterdayMITA35Claude Code
reference-builderechoVic/blade-codeAgent18124d agoMITA41Claude Code
bank-extractledq/resumeryAgent21mo agoMITA91Claude Code
doc-convertercoltonbearden/carrelAgent23d agoMITA61Claude Code
God Agent Apollo — Content AgentHolley-Studio/thesmos-governanceAgent210d agononeA38Claude Code
playwright-test-generatormicrosoft/playwrightAgent99kyesterdayApache-2.0A151Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginnersAgent79k4d agoMITA33Claude Code