VibeHarness: Command for Claude Code

.claude/commands/vibe-harness.md

vibe-harness is a command for Claude Code from ccivlcid/VibeHarness. It costs 0 tokens per session (153 once invoked), scanned A, original, MIT.

A command that makes the agent read a project's CLAUDE.md file and follow its rules. It can also read project status, technical notes, business plans, and reference documents when continuing work.

In plain words
What is it for?
Starting or continuing development in projects that keep instructions in CLAUDE.md, Progress.md, PROJECT_RULES.md, and related documentation.
Why use it?
It reduces the chance that the agent ignores the project's conventions or loses track of earlier decisions. The project documentation becomes the starting point for the work.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: mentions CLAUDE.md.

This is ccivlcid/VibeHarness's own configuration. It tells Claude Code how to work on VibeHarness 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 VibeHarness configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ccivlcid/VibeHarness. 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/ccivlcid/VibeHarness/main/.claude/commands/vibe-harness.md
Clone the repo
git clone --depth 1 https://github.com/ccivlcid/VibeHarness

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 vibe-harness

README.md
[![agentmods](https://agentmods.dev/badge/commands/ccivlcid/vibeharness/vibe-harness/github.svg)](https://agentmods.dev/commands/ccivlcid/vibeharness/vibe-harness)
Your own site
<a href="https://agentmods.dev/commands/ccivlcid/vibeharness/vibe-harness"><img src="https://agentmods.dev/badge/commands/ccivlcid/vibeharness/vibe-harness/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 vibe-harness

Your own site · 80×15
<a href="https://agentmods.dev/commands/ccivlcid/vibeharness/vibe-harness"><img src="https://agentmods.dev/badge/commands/ccivlcid/vibeharness/vibe-harness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 153 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 $0.00000 $0.00153
Opus 5 $0.00000 $0.00077
Sonnet 5 $0.00000 $0.00031
Haiku 4.5 $0.00000 $0.00015

Measured 10d ago against content hash 9ba58305b350, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

vibe-harness 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 10d 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/commands/vibe-harness.md · 19 lines

What it actually says

VibeHarness

Read CLAUDE.md first. All rules are defined in CLAUDE.md at the project root.

When this command is triggered:

  1. Read CLAUDE.md at the project root and follow all VibeHarness rules
  2. Read the relevant reference docs in docs/references/ as needed

Continuing Previous Work

When asked to continue work on an existing project:

  1. Read Progress.md — current status and remaining work
  2. Read PROJECT_RULES.md — tech stack and conventions
  3. Read docs/biz/ — planning intent
  4. Read docs/ai-dev/ — technical decision context
  5. Continue development

$ARGUMENTS

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. 10d ago First seen · 19 lines · 0 tokens per session scan A 9ba58305b350

Subscribe to this mod's changes

vibe-harness is a command published in the GitHub repository ccivlcid/VibeHarness (5 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 153 tokens. 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.