agentmods.dev

mockpost: Instructions file for Claude Code

CLAUDE.md

mockpost CLAUDE.md is an instructions file for Claude Code from reiarseni/mockpost. It costs 963 tokens per session, scanned A, original, MIT.

Repository instructions for contributing to MockPost, including its language, Git workflow, branch and issue conventions, and commit format. Conventional commits are a standard way to label changes such as features, fixes, and documentation.

In plain words
What is it for?
Use it when making or reviewing MockPost changes so repository artifacts are written in English and follow the project's naming, wording, and commit rules.
Why use it?
It gives an AI coding assistant the project rules needed to produce acceptable commits, branches, issues, pull requests, comments, and documentation.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

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

not rated 2repo 2mo ago A scan 963 tokens original MIT
View source ↗ reiarseni/mockpost
Reuse

Borrowing it

Nothing to install: this file belongs to reiarseni/mockpost. 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/reiarseni/mockpost/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/reiarseni/mockpost

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 mockpost CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/reiarseni/mockpost/claude-md/github.svg)](https://agentmods.dev/instructions/reiarseni/mockpost/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/reiarseni/mockpost/claude-md"><img src="https://agentmods.dev/badge/instructions/reiarseni/mockpost/claude-md/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 mockpost CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/reiarseni/mockpost/claude-md"><img src="https://agentmods.dev/badge/instructions/reiarseni/mockpost/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 963 This file is loaded in full into every session.
When invoked 963 The same file — it is already loaded in full.
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 $0.00963 $0.00963
Opus 5.5 $0.00385 $0.00385
Sonnet 5.5 $0.00193 $0.00193
Haiku 4.5 $0.00096 $0.00096

Measured 2mo ago against content hash b009b4392513, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mockpost CLAUDE.md 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.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — MockPost contribution workflow

This file documents the git workflow for MockPost: how commits, branches, issues and pull requests are named and structured. Every artifact must read as written by a senior developer — natural, concise, technical prose. No AI marks anywhere.

Language

All repository artifacts are in English: commit titles/bodies, branch names, issue titles/bodies, PR titles/bodies, code comments and docs. The only exception is communication in chat; everything committed is English.

Conventional commits

Format: <prefix>: <summary in third-person singular, max 72 chars>

Valid prefixes:

Prefix Use for
feat New capability, improvement, refactor, infrastructure
fix Bug correction or incorrect behavior
chore Maintenance, dependencies, CI/CD, packaging, technical cleanup
refactor Code restructuring without behavior change
docs Documentation only
test Tests only

Rules:

  • Summary in third-person singular ("adds X", "fixes Y") — never imperative ("add X").
  • No accents, no parentheses, max 72 characters.
  • Body — pick the case that applies, in order:
    • A — No body: title fully explains the change.
    • B — Short prose (small, unit-like change): 1-2 direct lines explaining the why or what for — not the what (that is the title/diff).
    • C — Bulleted justifications (diverse commit): one - line per area/reason.
  • Body lines: max 72 chars.
  • NEVER include Co-Authored-By or any AI attribution in any commit.
  • Footer: intermediate commits in a group use Refs #N; the last commit of the group uses Closes #N (N = issue number).

Branches

Pattern: <prefix>/<N>-<kebab-case-description>

  • Features, chores, spikes: feat/12-verificacion-otp (see language note below).
  • Bug fixes: fix/23-error-snapshot-nulo.
  • Description in kebab-case, lowercase, no accents.

Language note: commit titles and bodies are English, but branch descriptions stay in Spanish kebab-case by project convention. If you prefer English branches, say so once and it becomes the project rule.

Read the full file on GitHub · 95 lines

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 · 95 lines · 963 tokens per session scan A b009b4392513

Subscribe to this mod's changes

mockpost CLAUDE.md is an instructions file published in the GitHub repository reiarseni/mockpost (2 stars, last pushed 2mo ago), licensed MIT. It adds 963 tokens to every session, about $0.0039 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 2026-08-31.

CommitsGit and workflowapnsdevtoolsemail-testingemulatorfastapi
Related

mockpost CLAUDE.md compared with instructions from other repositories

mockpost CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mockpost CLAUDE.mdreiarseni/mockpostInstructions file22mo agoMITA963Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode