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/summarybotng/summarybot-ng/context-driven-testingnpx skills add summarybotng/summarybot-ng --skill context-driven-testinggit clone --depth 1 https://github.com/summarybotng/summarybot-ngWrote 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/summarybotng/summarybot-ng/context-driven-testing)<a href="https://agentmods.dev/skills/summarybotng/summarybot-ng/context-driven-testing"><img src="https://agentmods.dev/badge/skills/summarybotng/summarybot-ng/context-driven-testing.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00042 | $0.01545 |
| Opus 5 | $0.00021 | $0.00772 |
| Sonnet 5 | $0.00008 | $0.00309 |
| Haiku 4.5 | $0.00004 | $0.00154 |
Grade A, and why
context-driven-testing 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 today.
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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context-Driven Testing
<default_to_action> When making testing decisions or adapting approaches:
- ANALYZE context: project goals, constraints, risks, team skills
- QUESTION practices: "Why this? What risk does it address? What's the cost?"
- INVESTIGATE not just check: Does software solve the problem, or create new ones?
- ADAPT approach based on context, not "best practices"
- DOCUMENT discoveries, not pre-written plans
Quick Context Analysis:
- Mission: "Find important problems fast enough to matter" (not "execute test cases")
- Risk: Safety-critical = high rigor; internal tool = lighter touch
- Constraints: Startup with tight timeline ≠ enterprise with compliance
- Skills: Novice needs structure; expert adapts intuitively
Critical Success Factors:
- No "best practices" work everywhere - only good practices in context
- Testing is investigation, not script execution
- Context changes; your approach should too </default_to_action>
Quick Reference Card
When to Use
- Making testing decisions for new project
- Questioning "that's how it's done" dogma
- Adapting approach to specific constraints
- Exploratory testing sessions
Seven Context-Driven Principles
- Value of any practice depends on its context
- Good practices in context, no universal best practices
- People working together are most important
- Projects unfold in unpredictable ways
- Product is a solution - if problem not solved, product fails
- Good testing is challenging intellectual work
- Judgment and skill determine right things at right times
Context Factors
| Factor | Questions |
|---|---|
| Project | Business goal? User needs? Failure impact? |
| Constraints | Timeline? Budget? Team skills? Legacy? |
| Risk | Safety-critical? Regulated? High volume? |
| Technical | Stack quirks? Integrations? Observability? |
RST Heuristics
| Heuristic | Application |
|---|---|
| SFDIPOT | Structure, Function, Data, Interfaces, Platform, Operations, Time |
| Oracles | Consistency with history, similar products, expectations, docs |
| Tours | Business District, Historical, Bad Neighborhood, Tourist, Museum |
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.
- today First seen · 200 lines · 42 tokens per session scan A f736a5fce129
context-driven-testing is a skill published in the GitHub repository summarybotng/summarybot-ng (2 stars, last pushed 2mo ago), licensed MIT. It adds 42 tokens to every session and 1,545 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 2026-09-03.
Other skills, from other repositories
decision-heuristics
当用户在重大选择上纠结（换工作/买房/搬城/合伙/结婚）、列了利弊表还是拿不定主意时调用。 核心理念: 无法决定就答否; 三个重大决定(住哪/和谁/做什么)值得花一两年; 两个均等选择选短期更痛苦的路。 不适用于: 日常琐碎选择（晚饭吃什么）、信息查询。 Triggers: 纠结/拿不定主意/要不要/该不该/利弊/decision/hesitate/should I.
Cognitive Load Analyzer
Evaluate interface complexity by measuring information density, decision points, visual hierarchy, and task completion paths to reduce user cognitive burden.
Exploratory Test Charter Generator
Generate structured exploratory testing charters with focused missions, time-boxed sessions, risk-based areas, and standardized note-taking templates for systematic exploration.
self-skill
Meta-skill for detecting when a solved problem is worth packaging as a reusable skill, then scaffolding it. Runs automatically after completing any non-trivial task. Also use when explicitly asked to create, draft, or propose a new skill from something just built.
wayfinding-routing
Universeller Skill für LLM-Navigation, Orientierung und Ausfallsicherheit. Stellt aktives Wayfinding, Selbstorientierung und Wiederherstellungsheuristiken bereit, wenn Agenten mit Kontextdrift, fehlschlagenden Werkzeugen, Schleifen oder Sackgassen konfrontiert sind. Enthält die synonymen Strategien survival-routing…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.