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/create-implementation-plannpx skills add YourTechBud/coding-harness-config --skill create-implementation-plangit 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 | $0.00019 | $0.01753 |
| Opus 5 | $0.00010 | $0.00877 |
| Sonnet 5 | $0.00004 | $0.00351 |
| Haiku 4.5 | $0.00002 | $0.00175 |
Grade A, and why
create-implementation-plan 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create a complete implementation plan from the current brainstorming context. The plan will be read by fresh implementers and reviewers with no access to this conversation, so it must preserve the intent and decisions they cannot recover elsewhere while pointing them to repository knowledge they can inspect themselves.
If <remarks> is non-empty, treat it as the user's focus, scope, or emphasis.
Ground before writing
Mine the conversation for intent, decisions, constraints, rationale, rejected alternatives, and unresolved assumptions. Inspect the relevant repository code, documentation, ADRs, and engineering guidance rather than guessing.
Sort information deliberately:
- Capture conversation residue and the connective reasoning between parts of the implementation.
- Reference existing knowledge with a path or URL plus what to inspect and why; do not copy it into the plan.
- Reference code by file and symbol or concept, not line number.
- Redact secrets, credentials, PII, and other sensitive values.
Ask only about consequential gaps that repository inspection cannot resolve and for which choosing an answer would materially change the plan. Always surface a proposed public/API, wire-format, or database-schema break before committing to it. Otherwise, make a grounded recommendation, state material assumptions in the plan, and keep moving. Do not turn plan creation into a walkthrough; the goal of this command is the complete draft artifact.
Architectural stance
Plan for the cleanest design and simplest mental model the problem allows, not the smallest diff. Bold refactors and preparatory work are welcome when they make later implementation easier. Honor repository engineering guidance.
Intermediate phases do not need to preserve a working application or a green test suite. Intentional breakage is allowed only under the phase contracts below and must never be ambiguous: name the expected broken state, how the phase itself is verified, and where temporary debt is repaid. Distinguish intentional temporary breakage from permanent removal that belongs to the target architecture.
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 · 137 lines · 19 tokens per session scan A dd25b67ee23d
create-implementation-plan is a skill published in the GitHub repository YourTechBud/coding-harness-config (5 stars, last pushed 3d ago), licensed Apache-2.0. It adds 19 tokens to every session and 1,753 once invoked, about $0.0001 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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.