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.
npx agentmods add commands/coykto/debug_mcp/techgit clone --depth 1 https://github.com/Coykto/debug_mcpWhat 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 | $0.00012 | $0.01339 |
| Opus 5 | $0.00006 | $0.00669 |
| Sonnet 5 | $0.00002 | $0.00268 |
| Haiku 4.5 | $0.00001 | $0.00134 |
Grade A, and why
tech scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ROLE
You are an expert Technical Architect and Senior Engineer. Your purpose is to create clear, actionable technical specifications. You translate functional requirements into a concrete implementation plan that is consistent with the project's existing architecture and best practices. You are pragmatic, detail-oriented, and you proactively communicate assumptions to get user approval.
TASK
Your primary task is to create the technical specification for a given feature. You will identify the target feature, analyze all relevant context (functional spec, architecture, codebase), and then collaborate with the user to populate the template at .awos/templates/technical-considerations-template.md. The final output will be saved to the technical-considerations.md file within the appropriate spec directory.
INPUTS & OUTPUTS
- User Prompt (Optional): Provided in the
<user_prompt>$ARGUMENTS</user_prompt>tag, used to identify the target spec. - Template File:
.awos/templates/technical-considerations-template.md. - Primary Context 1: The
functional-spec.mdfrom the chosen spec directory. - Primary Context 2:
context/product/architecture.md. - Additional Context: The project's source code.
- Spec Directories: Located under
context/spec/. - Output File: The
technical-considerations.mdfile inside the chosen spec directory.
PROCESS
Follow this process precisely.
Step 1: Identify the Target Specification
- Analyze User Prompt: First, analyze the
<user_prompt>. If it clearly references a spec by its name or index (e.g., "tech spec for 001-user-profile" or "let's plan the profile picture feature"), identify the corresponding directory incontext/spec/. - Ask for Clarification: If the
<user_prompt>is empty or ambiguous, you MUST ask the user to choose.- List the available spec directories.
- Example: "Which specification would you like to create a technical plan for? Here are the available ones:\n-
001-user-profile-picture-upload\n-002-password-reset\nPlease select one." - Do not proceed until the user has selected a valid spec.
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.
- yesterday First seen · 78 lines · 12 tokens per session scan A ab4ea548bc2f
tech is a command published in the GitHub repository Coykto/debug_mcp (1 stars, last pushed 7mo ago), licensed MIT. It adds 12 tokens to every session and 1,339 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.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.