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.
npx agentmods add commands/ayushshanu/codebase-mcp-server/create-specsgit clone --depth 1 https://github.com/AyushShanu/CodeBase-MCP-ServerWhat 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 | $0.00018 | $0.01713 |
| Opus 5 | $0.00009 | $0.00856 |
| Sonnet 5 | $0.00004 | $0.00343 |
| Haiku 4.5 | $0.00002 | $0.00171 |
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.
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:
-
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) -
feature_title— human readable title in Title Case- Example: "Tree-sitter Parsing & AST Chunking" or "MCP Server (Version 1)"
-
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
-
branch_name— format:feature/<feature_slug>- Example:
feature/tree-sitter-chunking
- Example:
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, conventionsDECISIONS.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 userFLOW.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
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.
- yesterday First seen · 181 lines · 18 tokens per session scan A 01f1b27feb6c
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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.