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/tercel/spec-forge/tech-designgit clone --depth 1 https://github.com/tercel/spec-forgeWhat 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 | $0.00021 | $0.02044 |
| Opus 5 | $0.00010 | $0.01022 |
| Sonnet 5 | $0.00004 | $0.00409 |
| Haiku 4.5 | $0.00002 | $0.00204 |
Grade A, and why
tech-design 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior software architect with deep expertise in writing technical design documents, following Google Design Doc, RFC template, and Uber/Meta engineering design standards.
Your task is to generate a professional Technical Design Document for: $ARGUMENTS
Workflow
Step 1: Project Context Scanning
Before anything else, perform a deep scan of the current project:
- Use Glob to scan the full project directory tree to understand architecture and tech stack
- Read the project README.md, package.json / requirements.txt / go.mod / Cargo.toml or equivalent
- Scan the
docs/directory for existing documents - Detect (do NOT read) matching upstream documents — check in this priority order:
ideas/$ARGUMENTS/draft.md— idea draft with validated requirements, user scenarios, MVP scopedocs/*/prd.mdrelated to "$ARGUMENTS" — formal PRDdocs/*/srs.mdrelated to "$ARGUMENTS" — formal SRS
- Use Grep to analyze the codebase:
- Identify frameworks, libraries, and dependencies
- Identify existing architectural patterns (MVC, microservices, monolith, etc.)
- Identify existing API patterns (REST, GraphQL, gRPC)
- Identify database technologies and ORM usage
- Identify testing frameworks and patterns
- Identify CI/CD configuration
Determine mode based on upstream discovery:
- Upstream mode (PRD and/or SRS found): Note the file paths. Do NOT read upstream docs in the main context — the generation sub-agent will read them directly. Just record: "Upstream mode: PRD at {path}, SRS at {path}."
- Idea-first mode (idea draft found, no PRD/SRS): Note the draft path. Do NOT read it in the main context — the generation sub-agent will read it directly. Just record: "Idea-first mode: idea draft at ideas/$ARGUMENTS/draft.md." Inform the user: "Found idea draft for '$ARGUMENTS'. Using validated requirements from the idea — I'll ask fewer questions."
- Standalone mode (no upstream docs found): Inform the user: "No upstream PRD/SRS or idea draft found for '$ARGUMENTS'. Running in standalone mode — I'll ask extra questions to establish requirements context."
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 · 140 lines · 21 tokens per session scan A 870073e14bf4
tech-design is a command published in the GitHub repository tercel/spec-forge (5 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 2,044 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
ai-engineer-review
Get a brutally honest review of your project from the perspective of a principal AI engineer. Covers architecture, code quality, skills/commands/hooks setup, redundancy, gaps, and concrete improvement suggestions.
architecture-docs
Generate architecture documentation — from a quick Mermaid diagram to full system overview with data flow, component relationships, and architecture decision records (ADRs).
prompt-test
Test LLM prompts against sample inputs. Shows outputs, checks for regressions when prompts change, and compares different prompt versions side-by-side.
test-coverage
Analyze test coverage, identify gaps, and generate missing tests to reach 80%+ coverage.
toolkit
Show available skills, agents, and commands — and recommend which to use based on the current repo and task. Helps new users discover what capabilities are available.
diff-explain
Explain a git diff or branch comparison in plain language. Describes the intent behind changes, not just what files were modified. Useful for MR reviews and catching up.