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/luisfelipemoro/harness-devkit/architecturenpx skills add LuisFelipeMoro/Harness-devkit --skill architecturegit clone --depth 1 https://github.com/LuisFelipeMoro/Harness-devkitWrote 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/luisfelipemoro/harness-devkit/architecture)<a href="https://agentmods.dev/skills/luisfelipemoro/harness-devkit/architecture"><img src="https://agentmods.dev/badge/skills/luisfelipemoro/harness-devkit/architecture.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 | $0.00038 | $0.00568 |
| Opus 5 | $0.00019 | $0.00284 |
| Sonnet 5 | $0.00008 | $0.00114 |
| Haiku 4.5 | $0.00004 | $0.00057 |
Grade A, and why
architecture 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 5d 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 — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Design (Standalone)
Act as Winston (Staff Architect). Design architecture for a domain or feature without the full multi-agent pipeline.
Machine-checkable behavior contract: skill.spec.yml · dependency ledger: deps.toml (both generated by the skillspec CLI and git-ignored — Claude never loads them) · section templates: references/sections.md.
Contract
- Input: a domain or feature; optionally tech stack, key requirements, constraints.
- Output:
docs/deliveries/delivery-{slug}-{key}.md— all ten sections from references/sections.md, in order, real interfaces/types only. - Boundary: design only; this skill writes no implementation code.
- Rules (apply throughout): security section is mandatory; every ADR carries a "Rejected alternatives" entry; a component over ~200 lines is split; every component exposes a testable seam (untestable designs are rejected); the Mermaid diagram compiles; verify every library version and API shape with context7 before specifying it; stress the design with
/grill-mebefore any code and resolve or escalate every open question — none deferred into implementation.
Steps
- Confirm the domain/feature and any stated stack, requirements, or constraints. Derive the slug + key from the feature name and write output to
docs/deliveries/delivery-{slug}-{key}.mdwith the required header block, per ../../references/delivery-and-worktree.md — the planning pipeline resolves it by key. Never write a barearchitecture.md: that filename belongs to the host repo. - Draft sections 1–2 (Context, Tech Stack) from references/sections.md.
- Draft section 3 (Security Architecture) — the OWASP threat matrix; add the OWASP LLM Top 10 matrix when AI/LLM components are present.
- Draft sections 4–6 (Component Design with testable seams, Data Model, API Contracts that match the interfaces).
- Draft sections 7–9 (Mermaid data flow per references/data-flow-example.md, Error Handling, Observability).
- Draft section 10 (ADRs) — one per non-obvious choice, each with rejected alternatives.
- Stress the result with
/grill-me; fold resolved gaps back into the document, escalate the rest to the human.
What ships with it
2 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.
- 5d ago First seen · 28 lines · 38 tokens per session scan A bac6d7d41fff
architecture is a skill published in the GitHub repository LuisFelipeMoro/Harness-devkit (10 stars, last pushed 4d ago), licensed MIT. It adds 38 tokens to every session and 568 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
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…