Borrowing it
Nothing to install: this file belongs to shinpr/agentic-code. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/shinpr/agentic-code/main/.agents/skills/implementation-approach/SKILL.mdgit clone --depth 1 https://github.com/shinpr/agentic-codeWrote 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/shinpr/agentic-code/implementation-approach)<a href="https://agentmods.dev/skills/shinpr/agentic-code/implementation-approach"><img src="https://agentmods.dev/badge/skills/shinpr/agentic-code/implementation-approach/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/shinpr/agentic-code/implementation-approach"><img src="https://agentmods.dev/badge/skills/shinpr/agentic-code/implementation-approach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00022 | $0.00542 |
| Opus 5.5 | $0.00009 | $0.00217 |
| Sonnet 5.5 | $0.00004 | $0.00108 |
| Haiku 4.5 | $0.00002 | $0.00054 |
Grade A, and why
implementation-approach 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 2mo 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementation Approach
Strategy Selection
Use this sequence when a design or task needs an implementation approach:
- Current evidence: Inspect the relevant responsibility, data or control path, representative repository pattern, and constraints that can change the choice.
- Direct implementation: Describe the simplest end-to-end change that delivers the confirmed outcome through the existing architecture and dependencies.
- Failure check: Test the direct implementation against current requirements, verified constraints, observed problems, and evidence-backed material risks within scope.
- Targeted expansion: Add only what resolves a failed item. Compare the smaller design with and without the addition.
- Value and subtraction check: Retain an addition only when evidence shows that its outcome benefit justifies its implementation, testing, documentation, runtime, and maintenance cost.
Possible future reuse, generic best practice, speculative edge cases, and optional hardening are not failed items. File count is supporting evidence, not a strategy rule.
Keep unselected candidates in the active execution context. Create a durable artifact only for a named downstream consumer.
Slicing Choice
Choose the smallest structure that preserves real dependency order and yields observable progress:
- Vertical: One user- or consumer-visible outcome can be completed across its layers without first creating a shared foundation.
- Foundation-first: Multiple required outcomes depend on the same contract or mechanism that must exist before any can work.
- Hybrid: One verified shared dependency comes first, followed by outcome-oriented slices.
Create phases from verified dependencies rather than architecture layers. Keep independently executable work separate when combining it would obscure ownership or verification.
Verification Level
Select the narrowest level that exercises the boundary named by the requirement:
- L1: Local: A unit, pure transformation, local command, build, or artifact check.
- L2: Integration: Interaction across components, persistence, processes, or another named integration boundary.
- L3: End-to-end: The complete user, browser, process, or service journey required by the acceptance criterion.
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.
- 2mo ago First seen · 48 lines · 22 tokens per session scan A f4e88ce2807d
implementation-approach is a skill published in the GitHub repository shinpr/agentic-code (50 stars, last pushed 7d ago), licensed MIT. It adds 22 tokens to every session and 542 once invoked, about $0.0001 per session on Opus 5.5. 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
agent-user-tools
Agent skill for user-tools - invoke with $agent-user-tools.
todos
Use when the user asks for a shared plan, a task needs at least three substantive execution steps, or a loose TODO is pending. Without an explicit plan request, not for one-shot answers or checks, or one- to two-step work that is not already in the list.
moai-factory-foreman
One unattended factory foreman iteration: watch the backlog queue, dispatch the next operator-picked card to an isolated worker, collect completion evidence on read (not on claims), and report. This is the body the project's loop.md driver invokes each iteration of a bare /loop; it can also be invoked directly to test…
context-preservation
State capture and restore across context window compactions. Monitors usage thresholds and serializes quality, task, and spec state for seamless continuation.
cog-braindump-capture
Capture raw thoughts with automatic domain classification and vault routing.
cog-knowledge-consolidation
Build structured knowledge frameworks from scattered vault notes with source attribution.