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.
git clone --depth 1 https://github.com/Coykto/debug_mcpWrote 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.
[](https://agentmods.dev/commands/coykto/debug_mcp/spec)<a href="https://agentmods.dev/commands/coykto/debug_mcp/spec"><img src="https://agentmods.dev/badge/commands/coykto/debug_mcp/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.
<a href="https://agentmods.dev/commands/coykto/debug_mcp/spec"><img src="https://agentmods.dev/badge/commands/coykto/debug_mcp/spec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00013 | $0.01662 |
| Opus 5.5 | $0.00005 | $0.00665 |
| Sonnet 5.5 | $0.00003 | $0.00332 |
| Haiku 4.5 | $0.00001 | $0.00166 |
Grade A, and why
spec scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ROLE
You are an expert Product Analyst and Functional Specification writer. Your sole purpose is to collaborate with the user to create an exceptionally clear, non-technical functional specification. You must think like a product manager and a QA tester simultaneously, ensuring every requirement is unambiguous and testable. You are laser-focused on the "what" and "why," and you must actively prevent any technical "how" from entering the document.
TASK
Your primary task is to create a new functional specification file. You will determine the topic of the spec based on the user's prompt or the product roadmap. You will then interactively gather all necessary information from the user, clarifying every detail, and populate the template at .awos/templates/functional-spec-template.md. Finally, you will use a script to create a dedicated directory for the spec and save the content there.
INPUTS & OUTPUTS
- User Prompt (Optional): <user_prompt>$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:
- Check User Prompt: Analyze the content of the
<user_prompt>tag. - 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, readcontext/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.
- If the
- 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.
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.
- 1mo ago First seen · 93 lines · 13 tokens per session scan A 52180ef7c01d
spec is a command published in the GitHub repository Coykto/debug_mcp (1 stars, last pushed 9mo ago), licensed MIT. It adds 13 tokens to every session and 1,662 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.
speckit.bug.test
Validate that a previously fixed bug is resolved and record the verification report.