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/quasi/cl-mcp-server/devnpx skills add quasi/cl-mcp-server --skill devgit clone --depth 1 https://github.com/quasi/cl-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 | $0.00026 | $0.01877 |
| Opus 5 | $0.00013 | $0.00938 |
| Sonnet 5 | $0.00005 | $0.00375 |
| Haiku 4.5 | $0.00003 | $0.00188 |
Grade A, and why
cl-mcp-server-dev 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 2d 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.
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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cl-mcp-server — Dev Skill
MCP server providing 36 Common Lisp REPL tools to Claude. Thin application layer over the cl-mcp protocol library.
Quick Reference
# Load
sbcl --load cl-mcp-server.asd --eval "(ql:quickload :cl-mcp-server)"
# Run
sbcl --load cl-mcp-server.asd \
--eval "(ql:quickload :cl-mcp-server)" \
--eval "(cl-mcp-server:start)"
# Test
sbcl --load cl-mcp-server.asd \
--eval "(ql:quickload :cl-mcp-server/tests)" \
--eval "(asdf:test-system :cl-mcp-server)"
Architecture
Dependency graph:
digraph {
rankdir=LR
"cl-mcp-server" -> "cl-mcp" [label="protocol"]
"cl-mcp-server" -> "alexandria"
"cl-mcp-server" -> "trivial-backtrace"
"cl-mcp" -> "yason"
"cl-mcp" -> "opsis/conditions"
}
What cl-mcp owns: JSON-RPC 2.0 framing, stdio transport, MCP handshake, per-server tool registry, error recovery.
What cl-mcp-server owns: Session state, code evaluation, 36 REPL tool handlers.
start reduces to 3 calls:
(cl-mcp:make-server :name "cl-mcp-server" :version "0.3.0")
(cl-mcp-server.tools:define-builtin-tools server session)
(cl-mcp:run-server server)
Package Structure
| Package | File | Purpose |
|---|---|---|
cl-mcp-server.conditions |
src/conditions.lisp |
REPL conditions + re-exports from cl-mcp.conditions |
cl-mcp-server.error-format |
src/error-format.lisp |
Condition/backtrace formatting |
cl-mcp-server.session |
src/session.lisp |
Persistent *package* context and state |
cl-mcp-server.evaluator |
src/evaluator.lisp |
Safe evaluation with stream capture |
cl-mcp-server.introspection |
src/introspection.lisp |
Symbol/class/method inspection |
cl-mcp-server.asdf-tools |
src/asdf-tools.lisp |
ASDF/Quicklisp operations |
cl-mcp-server.profiling-tools |
src/profiling-tools.lisp |
Statistical and deterministic profiling |
cl-mcp-server.telos-tools |
src/telos-tools.lisp |
Telos intent introspection (graceful degradation; see RULE-007) |
cl-mcp-server.tools |
src/tools.lisp |
Registers all 36 tools via cl-mcp:register-tool |
cl-mcp-server |
src/server.lisp |
Entry point: start |
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.
- 2d ago First seen · 178 lines · 26 tokens per session scan A 1f9fe6587ba4
cl-mcp-server-dev is a skill published in the GitHub repository quasi/cl-mcp-server (36 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 1,877 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.