Borrowing it
Nothing to install: this file belongs to cl-ai-project/cl-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/cl-ai-project/cl-mcp/main/.claude/skills/dogfooding-cl-mcp/SKILL.mdgit clone --depth 1 https://github.com/cl-ai-project/cl-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/skills/cl-ai-project/cl-mcp/dogfooding-cl-mcp)<a href="https://agentmods.dev/skills/cl-ai-project/cl-mcp/dogfooding-cl-mcp"><img src="https://agentmods.dev/badge/skills/cl-ai-project/cl-mcp/dogfooding-cl-mcp/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cl-ai-project/cl-mcp/dogfooding-cl-mcp"><img src="https://agentmods.dev/badge/skills/cl-ai-project/cl-mcp/dogfooding-cl-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00042 | $0.07094 |
| Opus 5.5 | $0.00017 | $0.02838 |
| Sonnet 5.5 | $0.00008 | $0.01419 |
| Haiku 4.5 | $0.00004 | $0.00709 |
Grade A, and why
dogfooding-cl-mcp 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 10d 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 — 359 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dogfooding cl-mcp
Overview
Build a real mid-size Common Lisp project with cl-mcp's own tools, watching for every rough edge along the way. The point is not the project — it is the feedback. Every retry, every confusing error, every tool that surprises you goes into the ledger; what survives triage goes into the feedback file.
Core principle: Cheap, disposable projects that exercise the full cl-mcp tool surface produce better feedback than abstract review. Build, notice friction, find out which layer it lives in, record what that produced, throw the project away.
When to Use
- User asks for dogfooding, feedback collection, or "try cl-mcp on a real project"
- You want to verify a recent cl-mcp change works in practice, not just in unit tests
- You are looking for P1/P2/P3-level improvement candidates to feed into the next PR cycle
Do NOT use for: scaffolding a project the user actually wants to keep, or for unrelated CL work.
Workflow
1. Workspace setup
Scaffold projects live under experiments/ inside the cl-mcp checkout.
This directory is listed in .gitignore, so generated files never appear
in git status and cannot be committed by accident. Build and edit with the
root left at the cl-mcp checkout; step 5 switches it to the experiment for the
reference scan alone, and switches it straight back.
fs-set-project-root path=. # ensure project root is cl-mcp
fs-get-project-info # confirm
Hydrate deferred tool schemas before any tool call with boolean/integer parameters.
Without this, calls like load-system force=true or repl-eval print_length=N will fail
with misleading must be boolean/must be integer errors (harness-side issue, not cl-mcp):
ToolSearch select:mcp__cl-mcp__lisp-read-file,mcp__cl-mcp__load-system,mcp__cl-mcp__repl-eval,mcp__cl-mcp__inspect-object,mcp__cl-mcp__lisp-edit-form,mcp__cl-mcp__clgrep-search,mcp__cl-mcp__code-find,mcp__cl-mcp__code-describe,mcp__cl-mcp__code-find-references,mcp__cl-mcp__pool-kill-worker
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.
- 10d ago Changed · +27 lines 96e1e890ca5b
- 24d ago Changed ce7fb422079e
- 25d ago Changed · +1 lines fce848207ab6
- 26d ago Changed f97d6c45fbcc
- 1mo ago Changed 5f147abe1c4a
- 1mo ago Changed 8be7a4e863cb
- 1mo ago Changed · +100 lines 28ac6af2d7b9
- 2mo ago First seen · 231 lines · 42 tokens per session scan A 7e1a11ff16dd
dogfooding-cl-mcp is a skill published in the GitHub repository cl-ai-project/cl-mcp (90 stars, last pushed 9d ago), licensed MIT. It adds 42 tokens to every session and 7,094 once invoked, about $0.0002 per session on Opus 5.5. 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
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.