create-specs

A command that creates a written feature plan and a Git branch for the next development session of a code-search server. A Git branch is a separate line of work that keeps changes isolated.

In plain words
What is it for?
Use it to turn a day number, feature title, and short identifier into a planned feature branch after checking that the working folder is clean.
Why use it?
It standardizes the start of each build day and prevents work from starting when the project already has uncommitted changes.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/ayushshanu/codebase-mcp-server/create-specs
Clone the repo
git clone --depth 1 https://github.com/AyushShanu/CodeBase-MCP-Server

Made for: Claude Code.

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,713 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00018 $0.01713
Opus 5 $0.00009 $0.00856
Sonnet 5 $0.00004 $0.00343
Haiku 4.5 $0.00002 $0.00171

Measured yesterday against content hash 01f1b27feb6c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-specs 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 yesterday.

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/create-specs.md · 181 lines

How it starts

The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior AI/ML engineer spinning up the next build step for the Codebase RAG MCP Server — an AST-aware, hybrid-retrieval RAG system exposed to Claude Code/Claude Desktop over MCP. Always follow the rules in CLAUDE.md.

User input: $ARGUMENTS

Step 1 — Check working directory is clean

Run git status and check for uncommitted, unstaged, or untracked files. If any exist, stop immediately and tell the user to commit or stash changes before proceeding. DO NOT CONTINUE until the working directory is clean.

Step 2 — Parse the arguments

From $ARGUMENTS extract:

  1. day_number — zero-padded to 2 digits: 3 → 03, 12 → 12 (matches the day-by-day plan in CLAUDE.md — Day 1 = Foundation through Day 12 = Final QA + packaging)

  2. feature_title — human readable title in Title Case

    • Example: "Tree-sitter Parsing & AST Chunking" or "MCP Server (Version 1)"
  3. feature_slug — git and file safe slug

    • Lowercase, kebab-case
    • Only a-z, 0-9 and -
    • Maximum 40 characters
    • Example: tree-sitter-chunking, mcp-server-v1
  4. branch_name — format: feature/<feature_slug>

    • Example: feature/tree-sitter-chunking

If you cannot infer these from $ARGUMENTS, ask the user to clarify before proceeding.

Step 3 — Check branch name is not taken

Run git branch to list existing branches. If branch_name is already taken, append a number: feature/tree-sitter-chunking-01, -02 etc.

Step 4 — Switch to main and pull latest

Run:

git checkout main
git pull origin main

Step 5 — Create and switch to the feature branch

Run:

git checkout -b <branch_name>

Step 6 — Research the codebase

Read these before writing the spec:

  • CLAUDE.md — roadmap, architecture, stack options, conventions
  • DECISIONS.md — prior architecture/library decisions and their reasoning; do not silently re-decide something already settled here (e.g. which embedding model, which vector store) without flagging it to the user
  • FLOW.md — how data currently travels through the pipeline (ingestion → parsing → chunking → embedding → retrieval → rerank → generation → citations → MCP); understand what this day's feature plugs into before adding to it
  • The src/ subfolder(s) relevant to this day's pipeline stage
  • All files in .claude/specs/ — avoid duplicating existing specs

Read the full file on GitHub · 181 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. yesterday First seen · 181 lines · 18 tokens per session scan A 01f1b27feb6c

Subscribe to this mod's changes

create-specs is a command published in the GitHub repository AyushShanu/CodeBase-MCP-Server (1 stars, last pushed 3d ago), licensed MIT. It adds 18 tokens to every session and 1,713 once invoked, about $0.0001 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 2026-08-31.