serve

A way to run Cladding as an MCP server, a program that lets another coding tool use its tools, stored information, and prepared instructions. It communicates over standard input and output.

In plain words
What is it for?
Use it when exposing Cladding to another MCP client or when debugging the server by itself. It provides development checks, project information, audit records, role instructions, and live audit updates.
Why use it?
It lets a separate MCP-compatible client access Cladding's development and onboarding functions without calling them directly.

Skill for Claude CodeCodex

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 skills/qwerfunch/cladding/serve
Any agent
npx skills add qwerfunch/cladding --skill serve
Clone the repo
git clone --depth 1 https://github.com/qwerfunch/cladding

Made for: Claude Code, Codex.

Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 361 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 $0.00078 $0.00361
Opus 5 $0.00039 $0.00180
Sonnet 5 $0.00016 $0.00072
Haiku 4.5 $0.00008 $0.00036

Measured yesterday against content hash f08bbdbbfeb0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

serve 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.

plugins/antigravity/skills/serve/SKILL.md · 21 lines

What it actually says

Cladding serve

Run clad serve from the project root. Boots an MCP server over stdio that exposes:

  • Tools: the full development surface (feature/graph/context queries, checks, gate, changelog) plus the natural-language onboarding flow — clad_prepare_init / clad_stage_init / clad_init and the clarify pair. Before spec.yaml exists only the three onboarding bootstrap tools are exposed.
  • Resources: cladding://spec, cladding://events, cladding://audit.
  • Prompts: 5 personas (orchestrator, planner, reviewer, observability, developer).
  • Live audit notifications: notifications/resources/updated fires for cladding://audit whenever a new evidence entry lands — a subscribed client can live-tail the audit log without polling.

Registers itself in cladding's sampling context so the host adapters (generic-mcp, claude-code) route LLM dispatch through McpSamplingTransport instead of the Mock fallback.

clad serve --cwd /path/to/project

Most users don't run this directly. Cladding's plugin manifest (.mcp.json) launches clad serve automatically when the plugin is enabled. Invoke this skill only for debugging the MCP server in isolation.

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 · 21 lines · 78 tokens per session scan A f08bbdbbfeb0

Subscribe to this mod's changes

serve is a skill published in the GitHub repository qwerfunch/cladding (14 stars, last pushed 3d ago), licensed MIT. It adds 78 tokens to every session and 361 once invoked, about $0.0004 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 2026-08-30.

Related

Other skills, from other repositories

map-plan

ARCHITECT phase - decompose complex tasks into atomic subtasks with research, spec, and branch-scoped plan artifacts under .map.

azalio/map-framework · 31 tokens

map-review

Interactive 4-section code review using monitor, predictor, and evaluator agents plus the user and maintainer role reviewers on current changes. Use when reviewing a diff, PR, or staged work before merge. Do NOT use to plan or implement; use map-plan or map-efficient.

azalio/map-framework · 58 tokens

map-debug

Structured MAP debugging via task-decomposer, actor, and monitor agents. Use when reproducing a bug, isolating a regression, or diagnosing an error with specialized agents — including failing or flaky tests (pytest AssertionError), crashes and segmentation faults, memory-corruption or memory errors in native/C…

azalio/map-framework · 213 tokens

map-learn

Capture reusable lessons after a completed MAP workflow. Use when a MAP run has finished and you want rules written to .claude/rules/learned/ from a workflow summary or handoff. Do NOT use during active implementation.

azalio/map-framework · 51 tokens

map-efficient

State-machine MAP execution workflow for Codex. Use when implementing an approved MAP plan end to end, resuming from branch MAP taskplan or stepstate.json artifacts, or running non-trivial multi-subtask work. Use map-fast for tiny one-shot edits.

azalio/map-framework · 55 tokens

map-task

Execute a single subtask from an existing MAP plan via Actor and Monitor. Use when map-plan has decomposed work and you want fine-grained control over one subtask. Do NOT use without an existing plan; run map-plan first.

azalio/map-framework · 51 tokens