cranelisp: Agent for Claude Code

.claude/agents/spec.md

spec is an agent for Claude Code from alilee/cranelisp. It costs 15 tokens per session (227 once invoked), scanned A, original, MIT.

A language-specification agent role that records the rules of a programming language. Normative questions are referred to the user for a final decision.

In plain words
What is it for?
Use it to draft or maintain a language specification, examine assigned questions, and report evidence and unresolved decisions.
Why use it?
It gives specification work a defined authority boundary and prevents the agent from silently deciding disputed language behavior. It also requires project guidance and reporting.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; mentions CLAUDE.md.

This is alilee/cranelisp's own configuration. It tells Claude Code how to work on cranelisp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cranelisp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to alilee/cranelisp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/alilee/cranelisp/main/.claude/agents/spec.md
Clone the repo
git clone --depth 1 https://github.com/alilee/cranelisp

Made for: Claude Code.

Wrote 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.

agentmods badge for spec

README.md
[![agentmods](https://agentmods.dev/badge/agents/alilee/cranelisp/spec.svg)](https://agentmods.dev/agents/alilee/cranelisp/spec)
Your own site
<a href="https://agentmods.dev/agents/alilee/cranelisp/spec"><img src="https://agentmods.dev/badge/agents/alilee/cranelisp/spec.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 227 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 5.1 $0.00015 $0.00227
Opus 5 $0.00008 $0.00113
Sonnet 5 $0.00003 $0.00045
Haiku 4.5 $0.00002 $0.00023

Measured yesterday against content hash cc85030c98f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

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 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • training — 88% identical, 10 lines differ
.claude/agents/spec.md · 21 lines

What it actually says

Read and follow, in order: the repository root CLAUDE.md (and every CLAUDE.md applicable to the directories you touch), then sprints/METHOD.md for what cranelisp adds, then your role contract at .agents/skills/spec/SKILL.md — the contract governs your authority, boundaries and handoffs, and takes precedence over habit. Before work, load every support skill listed under always for spec in .agents/skill-composition.toml; when creating or editing a memory or standing document, also load those under standing_documents.

You are acting as the spec role. The dispatching coordinator's brief is your scope: do not silently expand it, and route work owned by other roles back to the coordinator per the contract's handoff rules. Report your results, your evidence, and any unresolved handoffs in your final message.

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 · 15 tokens per session scan A cc85030c98f6

Subscribe to this mod's changes

spec is an agent published in the GitHub repository alilee/cranelisp (7 stars, last pushed 6d ago), licensed MIT. It adds 15 tokens to every session and 227 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 2026-09-04.