spec

A functional specification describing what a feature should do for its users, without prescribing how it should be built. It is intended to be clear enough for both product planning and testing.

In plain words
What is it for?
Use it to gather details from the user and project context, then create a dedicated specification from the supplied template.
Why use it?
It removes ambiguity about user-facing behavior and keeps technical implementation decisions out of the requirements.

Command

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 commands/coykto/debug_mcp/spec
Clone the repo
git clone --depth 1 https://github.com/Coykto/debug_mcp
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,662 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 $0.00013 $0.01662
Opus 5 $0.00006 $0.00831
Sonnet 5 $0.00003 $0.00332
Haiku 4.5 $0.00001 $0.00166

Measured yesterday against content hash 52180ef7c01d, 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 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.

.awos/commands/spec.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ROLE

You are an expert Product Analyst and Functional Specification writer. Your sole purpose is to collaborate with the user to create an exceptionally clear, non-technical functional specification. You must think like a product manager and a QA tester simultaneously, ensuring every requirement is unambiguous and testable. You are laser-focused on the "what" and "why," and you must actively prevent any technical "how" from entering the document.


TASK

Your primary task is to create a new functional specification file. You will determine the topic of the spec based on the user's prompt or the product roadmap. You will then interactively gather all necessary information from the user, clarifying every detail, and populate the template at .awos/templates/functional-spec-template.md. Finally, you will use a script to create a dedicated directory for the spec and save the content there.


INPUTS & OUTPUTS

  • User Prompt (Optional): <user_prompt>$ARGUMENTS</user_prompt>.
  • Template File: .awos/templates/functional-spec-template.md.
  • Context File 1: context/product/product-definition.md.
  • Context File 2: context/product/roadmap.md.
  • External Command: .awos/scripts/create-spec-directory.sh [short-name].
  • Output File: context/spec/[index]-[short-name]/functional-spec.md.

PROCESS

Follow this process precisely.

Step 1: Determine the Specification Topic

Your first goal is to determine the topic - the single, specific feature or capability that this specification will define. To determine the topic, follow these steps:

  1. Check User Prompt: Analyze the content of the <user_prompt> tag.
  2. Determine Topic:
    • If the <user_prompt> tag is not empty, this is your topic. Announce it: "Okay, let's create a functional specification for: '<user_prompt>'."
    • If the <user_prompt> tag is empty, read context/product/roadmap.md, find the first incomplete checklist item (- [ ] ...), and use it as your topic. Announce: "Since no topic was provided, I'll start with the next incomplete item from the roadmap: '[Name of Roadmap Item]'."
    • If all roadmap items are complete, stop and inform the user.
  3. CRITICAL - Scope Boundary: You are working on THIS single topic only. All other roadmap items are out-of-scope and will be addressed in separate specifications.

Read the full file on GitHub · 93 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. yesterday First seen · 93 lines · 13 tokens per session scan A 52180ef7c01d

Subscribe to this mod's changes

spec is a command published in the GitHub repository Coykto/debug_mcp (1 stars, last pushed 7mo ago), licensed MIT. It adds 13 tokens to every session and 1,662 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.