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/kibiz-systems/kibuild-mcp/setup-kibuildgit clone --depth 1 https://github.com/KiBiz-Systems/kibuild-mcpWrote 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.
[](https://agentmods.dev/commands/kibiz-systems/kibuild-mcp/setup-kibuild)<a href="https://agentmods.dev/commands/kibiz-systems/kibuild-mcp/setup-kibuild"><img src="https://agentmods.dev/badge/commands/kibiz-systems/kibuild-mcp/setup-kibuild.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00020 | $0.01376 |
| Opus 5 | $0.00010 | $0.00688 |
| Sonnet 5 | $0.00004 | $0.00275 |
| Haiku 4.5 | $0.00002 | $0.00138 |
Grade C, and why
setup-kibuild scanned grade C with 2 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 4d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- macOS/Linux: `curl -fsSL https://raw.githubusercontent.com/priyabratasahoo21/kibuild-mcp/main/install.sh | sh` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- macOS/Linux: `curl -fsSL https://raw.githubusercontent.com/priyabratasahoo21/kibuild-mcp/main/install.sh | sh` How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the KiBuild MCP setup and verification wizard. Run each step below in order, autonomously. Only pause when you need a value the user must supply (project path). Report each step's result clearly.
Step 1 — Detect platform
Run uname -s && uname -m (macOS/Linux) or detect Windows via $ENV:OS.
Determine:
- Binary path:
/usr/local/bin/kibuild-mcp(macOS/Linux) or$env:LOCALAPPDATA\Programs\kibuild-mcp\kibuild-mcp.exe(Windows) - Config file:
~/.claude.json(macOS/Linux) or%USERPROFILE%\.claude.json(Windows) - Log file:
~/.fm_ai_bridge/mcp_server.log(macOS/Linux) or%USERPROFILE%\.fm_ai_bridge\mcp_server.log(Windows)
Step 2 — Check binary and version
Run kibuild-mcp --version (or full path if not in PATH).
If binary is missing: Install it now.
- macOS/Linux:
curl -fsSL https://raw.githubusercontent.com/priyabratasahoo21/kibuild-mcp/main/install.sh | sh- If curl not available:
wget -qO- https://raw.githubusercontent.com/priyabratasahoo21/kibuild-mcp/main/install.sh | sh - After install on macOS:
xattr -d com.apple.quarantine /usr/local/bin/kibuild-mcp 2>/dev/null || true
- If curl not available:
- Windows (PowerShell):
irm https://raw.githubusercontent.com/priyabratasahoo21/kibuild-mcp/main/install.ps1 | iex- If you get "running scripts is disabled": first run
Set-ExecutionPolicy -ExecutionPolicy RemoteSigned -Scope CurrentUser
- If you get "running scripts is disabled": first run
If binary is present but version is dev or older than v0.2.0: The binary is stale — it is missing explode_xml_export and generate_schema_map. Reinstall using the commands above.
Expected minimum version: v0.2.0 (adds explode_xml_export, generate_schema_map, load_skill, and --version flag).
Step 3 — Check MCP config
Read the Claude Code config file (~/.claude.json or %USERPROFILE%\.claude.json).
Check if a kibuild entry exists under mcpServers:
- If missing: ask the user for their project path and write it (see Step 4).
- If present: show the current
commandandKIBUILD_ACTIVE_PROJECTvalues and ask if they are correct.
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.
- 4d ago First seen · 107 lines · 20 tokens per session scan C ce5ba5198e74
setup-kibuild is a command published in the GitHub repository KiBiz-Systems/kibuild-mcp (6 stars, last pushed 2mo ago), licensed MIT. It adds 20 tokens to every session and 1,376 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
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.
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.