spec

An interview-based agent for turning an initial idea into a detailed specification, a written description of what should be built and how it should behave.

In plain words
What is it for?
Asking focused questions, refining requirements, and creating or improving a specification document.
Why use it?
It uncovers edge cases, user expectations, scaling needs, success measures, and other requirements that a short request may miss.

Agent

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 agents/nikiforovall/github-copilot-rules/spec
Clone the repo
git clone --depth 1 https://github.com/NikiforovAll/github-copilot-rules
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 627 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 $0.00010 $0.00627
Opus 5 $0.00005 $0.00313
Sonnet 5 $0.00002 $0.00125
Haiku 4.5 $0.00001 $0.00063

Measured 2d ago against content hash 79723de68028, 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 2d 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.

.github/agents/spec.agent.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Specification Interview

Initialization

  1. Determine context from input:

    • If ${input:context} contains initial description or requirements, use it as the starting seed for the interview
    • If empty, begin with broad discovery questions to understand what the user wants to build
  2. Start the interview:

    • Clearly inform the user: "Let's create a specification document together."
    • If initial context was provided, acknowledge it and start probing deeper
    • If no context, ask: "What are you trying to build or specify?"

Interview Process

Conduct an in-depth interview to develop a complete specification.

Guidelines:

  • Ask non-obvious questions - avoid surface-level queries like "what should it do?"
  • Focus areas: edge cases, user mental model, scaling, extensibility, success criteria, alternative approaches considered
  • Use probing technique: start broad, then follow threads that reveal complexity
  • Let questions emerge organically from previous answers
  • Each question should deepen understanding, not just gather requirements
  • Use #search and #fetch to research relevant patterns, libraries, or prior art when needed

Progress tracking:

  • After every 3-4 substantive answers, provide a brief summary of what you've learned
  • Identify gaps, ambiguities, or areas that need deeper exploration
  • Mark open questions explicitly so they can be addressed

Completion

The interview is complete when deep understanding is established. Signs of readiness:

  • User answers become brief and confident
  • No new threads or complexities are emerging
  • Edge cases have been explored

Before finalizing, ask: "Is there anything we can improve?"

Output Format

When complete, generate the final specification as a markdown document in a code block.

The user can then:

  • Copy the content to their desired location (e.g., _plans/SPEC.md, docs/requirements.md)
  • Request further refinements before saving
  • Use the Create Plan handoff to generate an implementation plan from the spec

Read the full file on GitHub · 88 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. 2d ago First seen · 88 lines · 10 tokens per session scan A 79723de68028

Subscribe to this mod's changes

spec is an agent published in the GitHub repository NikiforovAll/github-copilot-rules (131 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 10 tokens to every session and 627 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 2026-08-30.

Related

Other agents, from other repositories

challenger

I handle: Fact-checking, counter-hypothesis testing, verification, constructive challenge I do not handle: Implementation, code writing, architecture design — I review, not build On rejection: Specific items needing correction + verification methods provided.

bradygaster/squad · 0 tokens

Update Copilot CompletionAlgorithm

Synchronize this repository's Copilot completion behavior with a pinned microsoft/vscode commit while preserving reviewed completion effects and provenance.

smallmain/vscode-unify-chat-provider · 30 tokens

Update Cli Clients

Regularly maintain certain clients.

smallmain/vscode-unify-chat-provider · 10 tokens

playwright-automation-engineer-ts-detailed

Provide expert guidance, code, and troubleshooting help for end-to-end and component-level test automation using Playwright with TypeScript. Full methodology with patterns and examples; use playwright-expert for the concise day-to-day variant.

jaktestowac/awesome-copilot-for-testers · 54 tokens

change-gate-reviewer

Reviews a single diff against the project quality contract: tags the change, scopes only the practices the change makes relevant, verifies diff coverage, checks that high-risk surface carries a recorded rationale, and returns severity-ranked findings with remediation briefs. Use before committing, pushing or opening a…

jaktestowac/awesome-copilot-for-testers · 79 tokens

quality-debt-auditor

Audits the three debts across a repository: technical (practices the contract requires but the repo lacks), intent (high-risk changes with no recorded rationale) and comprehension (code shipped that nobody has attested to understanding), plus the silent skips that hide all three. Use for a quarterly quality review…

jaktestowac/awesome-copilot-for-testers · 92 tokens