spec

spec is a skill for Claude Code, Codex from ayberkyasa/tripod. It costs 74 tokens per session (1,041 once invoked), scanned A, original, MIT.

A guided planning process for starting a new software project. It interviews the user about the idea and records the agreed product requirements and development instructions in SPEC.md and CLAUDE.md files.

In plain words
What is it for?
Defining an app’s architecture, scope, platforms, accounts, and other requirements before implementation begins.
Why use it?
It turns an early, incomplete app idea into shared written decisions that future coding sessions can follow.

Skill for Claude CodeCodex

Part of the tripod plugin — 3 skills 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/ayberkyasa/tripod/spec
Any agent
npx skills add ayberkyasa/tripod --skill spec
Clone the repo
git clone --depth 1 https://github.com/ayberkyasa/tripod

Made for: Claude Code, Codex.

Or install tripod, the plugin that ships this one along with the rest of its 3 skills.

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/ayberkyasa/tripod/spec.svg)](https://agentmods.dev/skills/ayberkyasa/tripod/spec)
Your own site
<a href="https://agentmods.dev/skills/ayberkyasa/tripod/spec"><img src="https://agentmods.dev/badge/skills/ayberkyasa/tripod/spec.svg" alt="Measured on agentmods" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,041 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 $0.00074 $0.01041
Opus 5 $0.00037 $0.00521
Sonnet 5 $0.00015 $0.00208
Haiku 4.5 $0.00007 $0.00104

Measured 4d ago against content hash 00e3b9b5ca62, 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 4d 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.

skills/spec/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tripod: Spec

You are running phase 1 of the Tripod workflow. The outcome of this skill is exactly two files at the repository root: SPEC.md and CLAUDE.md. They will be two of the only three sources of truth for the entire project (the third, TASKS.md, comes later from /tripod:tasks). Everything you write here will be read by every future coding session, so precision now saves context forever.

Step 1 — Listen

Let the user describe the application in their own words. Do not interrupt with structure. If they invoked this skill without a description, ask for one: "Describe the app you want to build, in as much or as little detail as you like."

Step 2 — Interview in rounds

Ask clarifying questions in rounds of at most 3 questions. Never dump ten questions at once. After each round of answers, either ask the next round or declare the interview done. Two to three rounds is typical; stop as soon as the picture is clear.

Prioritize questions in this order — the earlier categories shape everything downstream:

  1. Architecture-defining decisions. Backend or fully local? Accounts or anonymous? Online or offline-first? Which platforms and minimum versions?
  2. MVP boundary. For every feature mentioned, decide: MVP or explicitly deferred? Push back gently on scope — a smaller MVP is almost always right. Propose the cut list; let the user veto.
  3. Forks in the road. Wherever more than one reasonable approach exists (data source, sync strategy, auth provider, UI paradigm), name the options with one-line trade-offs and ask the user to pick.
  4. Product feel. Design direction, tone, target user — one question at most; propose a default.

Where a sensible default exists, propose it instead of asking ("I'll assume offline-first with sync later — veto if wrong"). Users should veto, not design from scratch.

Step 3 — Write SPEC.md

Write SPEC.md at the repository root following templates/SPEC.template.md from this plugin (read it before writing). Quality bar:

Read the full file on GitHub · 60 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. 4d ago First seen · 60 lines · 74 tokens per session scan A 00e3b9b5ca62

Subscribe to this mod's changes

spec is a skill published in the GitHub repository ayberkyasa/tripod (2 stars, last pushed 19d ago), licensed MIT. It adds 74 tokens to every session and 1,041 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

artifact-conventions

Defines preservation, format, and section rules for SDD specification artifacts (spec.md, plan.md, tasks.md, checklists). Use when editing feature-artifact files under specs/ / to prevent accidental corruption of cross-referenced IDs, priorities, and gating state.

attilaszasz/sdd-pilot · 59 tokens

plan-authoring

Reference material for writing implementation plans (technical context, architecture decisions, data models, API contracts, project-instructions alignment). Loaded on demand by plan-feature; not directly invokable.

attilaszasz/sdd-pilot · 41 tokens

task-generation

Reference material with the canonical task-format grammar and decomposition rules for plan-to-tasks expansion. Loaded on demand by generate-tasks; not directly invokable.

attilaszasz/sdd-pilot · 35 tokens

adr-authoring

Defines the canonical MADR format, lifecycle rules, numbering policy, and SAD catalog contract for standalone ADRs under specs/adrs/.

attilaszasz/sdd-pilot · 30 tokens

implementation-standards

Reference material with coding standards (defensive coding, error handling, testing patterns). Loaded on demand by the Developer sub-agent (.github/agents/developer.md); not directly invokable.

attilaszasz/sdd-pilot · 44 tokens

spec-authoring

Reference material for writing product, technical, and operational specifications (work-item priorities, requirement families, success criteria). Loaded on demand by specify-feature; not directly invokable.

attilaszasz/sdd-pilot · 40 tokens