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/testing-strategynpx skills add shinpr/agentic-code --skill testing-strategygit 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 | $0.00032 | $0.00485 |
| Opus 5 | $0.00016 | $0.00243 |
| Sonnet 5 | $0.00006 | $0.00097 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
testing-strategy 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Strategy
Purpose
Select tests that prove an observable requirement at the lowest sufficient cost. Candidate discovery does not create an obligation to implement every technically valid test.
Selection Process
For each acceptance criterion that may require integration or E2E proof:
- Name the observable boundary: Identify the interaction, persisted effect, process, or user journey that must be proven.
- Check existing proof: Reuse or extend an established test when it already observes the required behavior.
- Select the narrowest level:
- use a unit or local check for isolated behavior;
- use integration when the requirement depends on a named component, persistence, or process boundary;
- use E2E only when the complete journey is itself the requirement.
- Compare cost: Consider setup, execution time, brittleness, maintenance, and diagnostic value using repository evidence rather than fixed universal scores.
- Retain necessary proof: Select a test only when a cheaper boundary cannot establish the required behavior or protect an accepted contract.
No new integration or E2E test is a valid conclusion when existing or cheaper proof is sufficient.
Priority
Prioritize proof for:
- core user or consumer journeys;
- shared or public contracts;
- persisted state transitions;
- security, authorization, compliance, or irreversible effects;
- integrations with demonstrated failure risk.
Priority does not determine test level. Use the narrowest boundary that can observe the prioritized behavior.
Deduplication
Before adding a test:
- search the existing suite for equivalent behavior;
- identify overlapping proof at other levels;
- extend existing coverage when that remains clear and maintainable;
- keep one representative proof when several candidates observe the same risk.
Selection Record
Record only decisions needed by planning or review:
Acceptance criterion: [identifier or behavior]
Selected proof: existing | local | integration | E2E | none
Boundary observed: [observable interaction or result]
Reason: [why this is the narrowest sufficient proof]
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 · 64 lines · 32 tokens per session scan A 39a5a74cdef5
testing-strategy is a skill published in the GitHub repository shinpr/agentic-code (49 stars, last pushed 3d ago), licensed MIT. It adds 32 tokens to every session and 485 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 2026-08-30.
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.