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 skills/qwerfunch/cladding/servenpx skills add qwerfunch/cladding --skill servegit clone --depth 1 https://github.com/qwerfunch/claddingWhat 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 | $0.00078 | $0.00361 |
| Opus 5 | $0.00039 | $0.00180 |
| Sonnet 5 | $0.00016 | $0.00072 |
| Haiku 4.5 | $0.00008 | $0.00036 |
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.
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_initand the clarify pair. Beforespec.yamlexists 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/updatedfires forcladding://auditwhenever 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.
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 · 21 lines · 78 tokens per session scan A f08bbdbbfeb0
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.
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.
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.
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…
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.
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.
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.