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 skills add zeeshanhanif/agentic-sdlc-kit --skill detailed-designgit clone --depth 1 https://github.com/zeeshanhanif/agentic-sdlc-kitWrote 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/skills/zeeshanhanif/agentic-sdlc-kit/detailed-design)<a href="https://agentmods.dev/skills/zeeshanhanif/agentic-sdlc-kit/detailed-design"><img src="https://agentmods.dev/badge/skills/zeeshanhanif/agentic-sdlc-kit/detailed-design/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/skills/zeeshanhanif/agentic-sdlc-kit/detailed-design"><img src="https://agentmods.dev/badge/skills/zeeshanhanif/agentic-sdlc-kit/detailed-design.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 | $0.00199 | $0.02310 |
| Opus 5 | $0.00100 | $0.01155 |
| Sonnet 5 | $0.00040 | $0.00462 |
| Haiku 4.5 | $0.00020 | $0.00231 |
Grade A, and why
detailed-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 9d 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Detailed Design (per feature)
The first loop skill: it runs once per vertical slice, for the life of the
project, turning a feature's planned intent into a buildable technical design —
the backend/system half of the feature's low-level design (ui-design is the
presentation half, and consumes this skill's contracts).
Three principles govern it:
- The feature's what is fixed upstream; this skill designs the how. The FR/UC IDs the feature implements were assigned and verified in requirements; the plan chose and scoped the feature. This skill never invents or reinterprets requirements — that inheritance-by-ID is exactly what keeps per-feature design consistent at scale.
- The live codebase is an input, not an obstacle. Feature N is designed months after feature 1, in a fresh session, against code that has evolved past the skeleton. Design against reality: the contracts, schema migrations, and conventions earlier features established. A design that conflicts with existing code is wrong even if it matches the documents.
- Depth here, and only here. This is where the pipeline's depth-on-demand promise is kept: full concrete detail for this feature — contracts, columns, components, tasks — and nothing for features that haven't reached the front.
Inputs
Defaults below; user-provided paths win; source-gated citation throughout (cite FR/UC/SCR/ADR IDs only when their documents exist; never fabricate).
- Implementation plan —
docs/implementation-plan.md. Which feature is next (or the user names one), its traced touchpoints: FRs implemented, UCs realized, SCR screens, building blocks/endpoints, data. - SRS —
docs/srs.md. The verbatim FR statements (they become acceptance criteria) and relevant NFRs (they constrain the design — cite them). - Use cases —
docs/use-cases.md. The UC flows the feature realizes — main/alternate/exception paths drive endpoint behavior and error design. - Architecture —
docs/architecture.md. The conceptual domain model (entity ownership, consistency boundaries), the ADRs constraining this feature, cross-cutting concepts (auth, error handling, observability conventions the design must follow). - The live codebase — mandatory read, not optional: existing route/contract
patterns, the current schema and migration history, module boundaries,
shared utilities, conventions in
docs/scaffold-notes.mdand the agent-instructions file. Prior feature designs live indocs/features/. - UX foundations —
docs/ux-foundations.md, light touch: the SCR screens' stated purpose/states, as context for what the contracts must serve.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 193 lines · 199 tokens per session scan A c681973578ff
detailed-design is a skill published in the GitHub repository zeeshanhanif/agentic-sdlc-kit (5 stars, last pushed 13d ago), licensed Apache-2.0. It adds 199 tokens to every session and 2,310 once invoked, about $0.0010 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…