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/codagent-ai/agent-skills/designnpx skills add Codagent-AI/agent-skills --skill designgit clone --depth 1 https://github.com/Codagent-AI/agent-skillsWrote 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/codagent-ai/agent-skills/design)<a href="https://agentmods.dev/skills/codagent-ai/agent-skills/design"><img src="https://agentmods.dev/badge/skills/codagent-ai/agent-skills/design.svg" alt="Measured on agentmods" 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 | $0.00043 | $0.00504 |
| Opus 5 | $0.00022 | $0.00252 |
| Sonnet 5 | $0.00009 | $0.00101 |
| Haiku 4.5 | $0.00004 | $0.00050 |
Grade A, and why
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 4d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design
Turn approved specifications into an implementation-ready technical design. Requirements are already settled; focus on architecture, component boundaries, interfaces, data flow, failure handling, migration, testing, and meaningful trade-offs.
Do not implement, scaffold, or invoke an implementation skill before the user approves the design.
Process
- Read every specification, including deferred-to-design markers, and inspect the relevant code, interfaces, tests, and repository conventions.
- Use
codagent:ask-questionsfor consequential architectural choices that repository context cannot safely resolve. Evaluate options first, recommend a path, and decide low-risk implementation details yourself. - Compare plausible approaches when a real trade-off exists. Do not manufacture alternatives for an obvious, patterned solution.
- Present a design scaled to the change's complexity. Cover the important components, interactions, decisions, risks, verification strategy, and any resulting specification implications; use diagrams when they clarify the design.
- After approval, write
design.mdand apply any specification changes revealed by the design, including completing deferred scenarios, only when those implications were presented with the approved design. Return to the user for a newly discovered behavioral or scope decision. Keep normative behavioral changes in specs and technical rationale in the design.
If design work exposes a product or scope decision rather than a technical implication, discuss it with the user instead of silently inventing behavior. The written artifacts must be self-contained for an implementing agent with no conversation history.
Do not invoke another lifecycle skill after writing.
Artifact template
Omit sections that do not apply.
## Context
<!-- Relevant current state and constraints. -->
## Goals / Non-Goals
**Goals:**
<!-- Outcomes this design enables. -->
**Non-Goals:**
<!-- Explicit exclusions. -->
## Approach
<!-- Components, interfaces, interactions, data flow, and failure behavior. -->
## Decisions
<!-- Consequential choices and rationale. -->
## Risks / Trade-offs
<!-- Material risks, mitigations, and alternatives considered. -->
## Migration Plan
<!-- Rollout and rollback when applicable. -->
## Open Questions
<!-- Only unresolved decisions that remain. -->
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.
- 4d ago First seen · 76 lines · 43 tokens per session scan A 78d69a69d1c6
design is a skill published in the GitHub repository Codagent-AI/agent-skills (30 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 504 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…