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/shinpr/agentic-code/implementation-approachnpx skills add shinpr/agentic-code --skill implementation-approachgit clone --depth 1 https://github.com/shinpr/agentic-codeWhat 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 | $0.00022 | $0.00542 |
| Opus 5 | $0.00011 | $0.00271 |
| Sonnet 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 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 — 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.
- 2d 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 (49 stars, last pushed 3d ago), licensed MIT. It adds 22 tokens to every session and 542 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 2026-08-30.
Other skills, from other repositories
agent-release-manager
Agent skill for release-manager - invoke with $agent-release-manager.
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
agent-pagerank-analyzer
Agent skill for pagerank-analyzer - invoke with $agent-pagerank-analyzer.
agent-pseudocode
Agent skill for pseudocode - invoke with $agent-pseudocode.
agent-code-analyzer
Agent skill for code-analyzer - invoke with $agent-code-analyzer.
agent-performance-analyzer
Agent skill for performance-analyzer - invoke with $agent-performance-analyzer.