A tool that turns an already-agreed conversation into a written capability specification. It saves the specification in a stable project record without starting the discussion again.

Use it to create or update specs, check the project structure and existing records, render the result, and run checks for specification problems.

It preserves decisions, assumptions, open questions, and acceptance conditions in one place instead of leaving them scattered across chat messages.

to-spec — Skill for Claude Code by KaydenClark

Install

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.

Any agent

npx skills add KaydenClark/LLM_Workbench --skill to-spec

Clone the repo

git clone --depth 1 https://github.com/KaydenClark/LLM_Workbench

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/kaydenclark/llm_workbench/to-spec/github.svg)](https://agentmods.dev/skills/kaydenclark/llm_workbench/to-spec)

Your own site

<a href="https://agentmods.dev/skills/kaydenclark/llm_workbench/to-spec"><img src="https://agentmods.dev/badge/skills/kaydenclark/llm_workbench/to-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/kaydenclark/llm_workbench/to-spec"><img src="https://agentmods.dev/badge/skills/kaydenclark/llm_workbench/to-spec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 415 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00022	$0.00415
Opus 5	$0.00011	$0.00208
Sonnet 5	$0.00004	$0.00083
Haiku 4.5	$0.00002	$0.00042

Measured yesterday against content hash 5823f67800f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

to-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.

skills/to-spec/SKILL.md · 37 lines

What it actually says

To Spec

Synthesize the current already-settled conversation into one stable capability record at the specs lane declared by workbench/manifest.json (normally workbench/specs/S-###-slug/SPEC.md). Do not restart grilling or implement the capability.

Verify the project root, nearest controls, existing specs, and relevant source or tests. Reuse an existing owning spec when the capability already has one; otherwise allocate the next unused stable ID and path.
Separate confirmed decisions from assumptions and unresolved owner choices. Record unresolved choices as blockers instead of inventing answers.
Capture the outcome, why it matters, verified current state, desired behavior, decisions/contracts, non-goals, dependencies, acceptance, test seams, documentation impact, and append-only evidence structure.
Set the normal stance in the assigned SPEC and each TASK (ticket) during authorized planning, usually Builder for implementation; do not make arriving agents select or record their own stance.
Seed Vertical Implementation Slices only with the smallest vertical tracer bullet needed to make the capability schedulable, cut with the /tracer-bullet discipline so it pierces every layer of the stack. Use /to-tickets later for detailed decomposition.
Preserve project vocabulary from LEXICON.md and cross-cutting boundaries from BLUEPRINT.md. A spec owns one capability; it replaces neither.
Run node workbench/tools/spec-workbench.mjs render and node workbench/tools/spec-workbench.mjs doctor, then report the spec path, open owner gates, and next eligible action.

Do not publish a parallel tracker record, create a transient requirements file, or claim verification that did not run.

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.

yesterday Changed · +5 lines 5823f67800f0
8d ago First seen · 32 lines · 22 tokens per session scan A 06f27d04e36d

Subscribe to this mod's changes

to-spec is a skill published in the GitHub repository KaydenClark/LLM_Workbench (2 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 415 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 2026-08-31.

Planning

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens