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-spec/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-spec)<a href="https://agentmods.dev/skills/cl-ai-project/cl-mcp/dogfooding-cl-spec"><img src="https://agentmods.dev/badge/skills/cl-ai-project/cl-mcp/dogfooding-cl-spec/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-spec"><img src="https://agentmods.dev/badge/skills/cl-ai-project/cl-mcp/dogfooding-cl-spec.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00061 | $0.06580 |
| Opus 5.5 | $0.00024 | $0.02632 |
| Sonnet 5.5 | $0.00012 | $0.01316 |
| Haiku 4.5 | $0.00006 | $0.00658 |
Grade A, and why
dogfooding-cl-spec 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 — 439 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dogfooding cl-spec
Overview
Repair a bug in a throwaway project that carries cl-spec contracts, using only
the four spec-* tools plus the ordinary cl-mcp tools. Record every place the
first-class tools were not enough and every response field that was misread.
Core principle: the question is not "which tools are missing" — it is can an agent read a contract, change the code, and tell verified from unverified. A missing operation is a measurement (how often, how painful), not a conclusion. Three to five recorded cycles decide what gets built; one frustrating moment does not.
This differs from dogfooding-cl-mcp, which measures tool-surface breadth.
Here the project is small and the epistemics are the subject: what the run
proved, what it did not, and whether the agent claimed more than it measured.
When to Use
- User asks for cl-spec dogfooding, spec-driven development feedback, or "try the spec tools on a real task"
- A new
spec-*tool (spec-check-call,spec-impact,spec-coverage, …) is being considered and nobody has measured whether therepl-evalfallback is actually painful - You changed the adapter (
src/spec-adapter-*.lisp,src/tools/spec-*.lisp) and want evidence beyond unit tests
Do NOT use for: exercising the whole cl-mcp tool surface (use
dogfooding-cl-mcp), or for a project the user intends to keep.
The Iron Rule of this skill
Do not implement a new tool during a dogfooding cycle. Not spec-check-call,
not spec-coverage, not a convenience wrapper. The cycle's output is a ledger,
and a cycle that "fixed" its own friction measured nothing. Adding tools is a
separate PR, after three cycles, and only for friction classed C or D
(see Fallback ledger).
repl-eval is an allowed escape hatch. Using it without recording it is the
one way to fail a cycle outright.
Setup
Scaffolds live under experiments/ inside the cl-mcp checkout (gitignored, so
generated files never reach git status). The feedback file is
claudedocs/dogfooding-cl-spec-feedback.md (also gitignored) unless the user
named another — append, never overwrite.
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 dc4329aa166a
- 1mo ago Changed · +1 lines 6f620aea15be
- 1mo ago First seen · 438 lines · 61 tokens per session scan A a88938c14a10
dogfooding-cl-spec is a skill published in the GitHub repository cl-ai-project/cl-mcp (90 stars, last pushed 9d ago), licensed MIT. It adds 61 tokens to every session and 6,580 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 2026-09-21.
Other skills, from other repositories
engram-testing-coverage
TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.
principle-test-behavior-not-implementation
Apply when you write, change, or keep a test. Assert what the code's users can observe, so that the test fails when that behavior breaks and keeps passing when only the internals change.
conductor-implement
Execute tasks from a track's implementation plan following TDD workflow.
tdd
This skill should be used when the user wants to implement features or fix bugs using test-driven development. Enforces the RED-GREEN-REFACTOR cycle with vertical slicing, context isolation between test writing and implementation, human checkpoints, and auto-test feedback loops. Uses multi-agent orchestration with the…
mobiai-mobile-tdd
You MUST use this before writing any implementation code for a mobile feature, bug fix, refactor, or behavior change. Tests come before implementation — no exceptions.
iterative-development
TDD iteration loops using Claude Code Stop hooks - runs tests after each response, feeds failures back automatically.