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 skills/clownware/product-dev/tech-specnpx skills add clownware/product-dev --skill tech-specgit clone --depth 1 https://github.com/clownware/product-devWhat 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 | $0.00036 | $0.01445 |
| Opus 5 | $0.00018 | $0.00723 |
| Sonnet 5 | $0.00007 | $0.00289 |
| Haiku 4.5 | $0.00004 | $0.00145 |
Grade A, and why
tech-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.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a technical architect helping translate product requirements into implementation-ready specifications. Your role is to produce precise, unambiguous specs that a developer can build from without guessing. Prefer specificity over flexibility — it's easier to loosen a tight spec than tighten a loose one.
Gate Check
Before starting, read .product-dev/context.json and verify:
solution_concept(required)user_flow(required)
If either is missing:
"Technical specs need design artifacts that don't exist yet. Missing: [list]. Run
/product-dev:ideato build a solution concept, then the product-flow skill to map the user flow."
Do not hard-block — if the user insists, proceed with available artifacts and explicitly note assumptions where inputs are missing.
Also read if available: screen_inventory, prototype_scope, hypothesis_statement.
Execution
Always spawn the Tech Spec Writer subagent (plugin/agents/tech-spec-writer.md). This skill delegates to the subagent because spec writing benefits from focused context and structured output.
The subagent runs the tech requirements prompt sequence from ${CLAUDE_PLUGIN_ROOT}/prompts/02_tech_requirements/:
Tier 1 Sequence
| Step | Prompt Path | Produces | Requires |
|---|---|---|---|
| 1 | 01_data_models/01_data_model.md |
data_models |
solution_concept, user_flow |
| 2 | 02_api_contracts_interfaces/01_define_api_endpoints.md |
api_contracts |
data_models, user_flow |
| 3 | 03_business_logic_rules/01_define_business_rules.md |
business_rules |
data_models, user_flow |
| 4 | 04_non_functional_requirements/01_performance_requirements.md |
nfr |
data_models, api_contracts, user_flow |
Context-Gated Handling
- Step 2 (
define-api-endpoints): Gate: "Client-server architecture."- If skipping: "API endpoint specs define the contract between frontend and backend — routes, request/response schemas, error codes, auth requirements. Since this is a local-only app (or CLI tool, hardware product, etc.), there's no client-server boundary to spec. If you later add a web API or mobile backend, revisit this step — it produces
endpoints.yamlfor the spec package." - When skipping, step 4 (
nfr) dropsapi_contractsfrom its requires and skips endpoint-specific performance targets.
- If skipping: "API endpoint specs define the contract between frontend and backend — routes, request/response schemas, error codes, auth requirements. Since this is a local-only app (or CLI tool, hardware product, etc.), there's no client-server boundary to spec. If you later add a web API or mobile backend, revisit this step — it produces
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.
- 2d ago First seen · 96 lines · 36 tokens per session scan A b5953bf4ed59
tech-spec is a skill published in the GitHub repository clownware/product-dev (3 stars, last pushed 6d ago), licensed Apache-2.0. It adds 36 tokens to every session and 1,445 once invoked, about $0.0002 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 skills, from other repositories
feature-flags
Use when feature flag tests fail, flags need updating, understanding @gate pragmas, debugging channel-specific test failures, or adding new flags to React.
frontend-unit-testing
Write comprehensive, behaviour-driven unit tests for Gradio frontend Svelte components using Vitest browser mode, Playwright, and the @self/tootils test utilities.
gradio-themes
Build and customise Gradio themes. Use when creating, editing, or publishing Python-based Gradio themes that control colours, typography, spacing, shadows, and dark mode.
hf-gradio
Use Gradio applications via API. Use when the user asks for to generate a prediction from a Gradio app on Hugging Face spaces or public URL. For example, "Generate an image using black-forest-labs/FLUX.2-dev".
compiler-port
Port a compiler pass from TypeScript to Rust. Gathers context, plans the port, implements in a subagent with test-fix loop, then reviews.
flags
Use when you need to check feature flag states, compare channels, or debug why a feature behaves differently across release channels.