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/yourtechbud/coding-harness-config/design-programnpx skills add YourTechBud/coding-harness-config --skill design-programgit clone --depth 1 https://github.com/YourTechBud/coding-harness-configWhat 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 | $0.00031 | $0.01091 |
| Opus 5 | $0.00015 | $0.00545 |
| Sonnet 5 | $0.00006 | $0.00218 |
| Haiku 4.5 | $0.00003 | $0.00109 |
Grade A, and why
design-program 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Program
Translate the supplied story and target architecture into an exact, maintainable program design grounded in the existing codebase. Treat the story as immutable product scope, use the current-state and architecture artifacts as working engineering context, and write the complete design at the requested path so implementation planning can organize the work without inventing consequential contracts, representations, behavior, or code structure.
Specify every decision whose alternatives could materially affect contracts, maintainability, behavior, or testability. Leave locally interchangeable implementation details open.
Artifact Contract
Cover the following knowledge in the form that best fits the system and story:
- Design basis and resolved target: Identify the story and predecessor artifacts, state the concrete program-level result, and distinguish verified repository facts, inherited architecture decisions, and proposed program-design choices. Preserve the architecture's intended system shape while resolving the code-level decisions it deliberately deferred.
- Program structure and collaboration: Define the load-bearing module layout, responsibilities, dependencies, and placement of new behavior. Name exact repository homes and important existing or proposed symbols. Explain consequential additions, removals, moves, and reuse, and trace important entry points through their collaborators to observable results. Use compact file-tree or call-path views when they make layout or control flow easier to inspect.
- Contracts and representations: Define exact changed external and cross-module contracts, including applicable APIs, routes, events, schemas, queries, persisted representations, configuration, and wire formats. Define consequential internal types and function or method signatures. State identity, ownership, lifetime, optionality, mutability, validation, preconditions, postconditions, and representation invariants where they affect correctness. When a boundary changes, turn the architecture's compatibility policy into concrete compatibility and migration mechanics.
- Behavioral mechanics: Specify the detailed success and failure paths, state transitions, data transformations, and component collaboration. Settle ordering, concurrency, transaction boundaries, idempotency, cancellation, timeout, retry, stale-data, and partial-failure behavior when relevant. For user-interface work, define consequential interaction states, focus and keyboard behavior, accessibility semantics, and recovery. Use examples, state tables, sequence descriptions, or focused pseudocode where they remove material ambiguity.
- Verification and operability design: Identify test seams, scenario classes, important fixtures, invariants, and observable outcomes. Connect consequential edge cases to the level of testing that can establish them. Define logging, metrics, diagnostics, or audit behavior when the change needs operational evidence. Describe what must be verifiable without assigning checks to implementation phases.
- Traceability and remaining risk: Account for every story outcome and relevant architecture decision. Connect each to its concrete code owner, contracts, flows, failure behavior, and verification seam. Converge on one recommended program design. For material uncertainty, select and justify an assumption, state the consequence if it is wrong, and explain how downstream work can verify it.
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 · 44 lines · 31 tokens per session scan A 24a1ad1ba4c9
design-program is a skill published in the GitHub repository YourTechBud/coding-harness-config (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 31 tokens to every session and 1,091 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.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
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…