spec

spec is a skill for Claude Code, Codex from pandysp/claude-plugins. It costs 88 tokens per session (806 once invoked), scanned A, original, MIT.

A structured implementation document that defines the goal, boundaries, completion checks, and verification for a coding task.

In plain words
What is it for?
Use it after choosing a design and before implementation, especially when another person or agent may execute the work.
Why use it?
It gives the person implementing the work a shared target and makes success testable before code is written.

Skill for Claude CodeCodex

Part of the spec plugin — 1 skill shipped together

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.

agentmods
npx agentmods add skills/pandysp/claude-plugins/spec
Any agent
npx skills add pandysp/claude-plugins --skill spec
Clone the repo
git clone --depth 1 https://github.com/pandysp/claude-plugins

Made for: Claude Code, Codex.

Or install spec, the plugin that ships this one along with the rest of its 1 skill.

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/skills/pandysp/claude-plugins/spec.svg)](https://agentmods.dev/skills/pandysp/claude-plugins/spec)
Your own site
<a href="https://agentmods.dev/skills/pandysp/claude-plugins/spec"><img src="https://agentmods.dev/badge/skills/pandysp/claude-plugins/spec.svg" alt="Measured on agentmods" height="20"></a>
Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 806 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 $0.00088 $0.00806
Opus 5 $0.00044 $0.00403
Sonnet 5 $0.00018 $0.00161
Haiku 4.5 $0.00009 $0.00081

Measured 3d ago against content hash 0ec2bbd222d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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.

plugins/spec/skills/spec/SKILL.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec: write the implementation specification

After the design is chosen, the spec is what the agent reads while implementing. Its job is to make success checkable before any code exists: bind the goal, the definition of done, the boundaries, and the verification into one durable artifact a fresh-context implementer (or verifier) could execute without re-deciding.

The spec specifies what done looks like, not a keystroke-by-keystroke route. State outcomes and constraints; trust the implementer to find the path. Spec quality depends on prior exploration of the relevant code. If you haven't explored, do that first.

Structure

Goal & why

What outcome this produces, who it's for, and what prompted it. The intent matters as much as the task: it lets the implementer connect the work to the right context instead of inferring it. One paragraph.

Definition of Done

The most important section. A checklist of acceptance criteria, each verifiable by a command to run or an observation to make, written so a fresh-context verifier could mark each one pass or fail without asking a question. "GET /api/users returns 200 with a list matching the schema", not "the endpoint works." This is the contract; everything else serves it.

Boundaries

What this change must NOT do: non-goals, files or systems to leave untouched, scope explicitly deferred. The failure mode here is overreach: unrequested refactors, defensive scaffolding, and abstractions for hypothetical futures. Name the edges so they aren't crossed silently.

Terrain (advisory)

Pointers from exploration, not a prescribed route. Deviate when the code says otherwise.

  • Likely files to touch: path/to/file, why it's in scope.
  • Existing utilities to reuse: path/to/util, what it does and why it fits. (Empty here is a red flag on non-greenfield work. Grep before concluding nothing fits.)

Verification

How the Definition of Done gets proven end-to-end: the commands to run, browser steps to take, and expected outputs (happy path and the most likely failure modes). For long-running work, state a self-check cadence: verify against the DoD at intervals, ideally with a fresh-context subagent, rather than only at the end.

Read the full file on GitHub · 43 lines

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. 3d ago First seen · 43 lines · 88 tokens per session scan A 0ec2bbd222d3

Subscribe to this mod's changes

spec is a skill published in the GitHub repository pandysp/claude-plugins (5 stars, last pushed 12d ago), licensed MIT. It adds 88 tokens to every session and 806 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

systematic-debugging

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

obra/superpowers · 21 tokens

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.

obra/superpowers · 37 tokens

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.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens