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/vladkesler/initrunner/edge-case-generationnpx skills add vladkesler/initrunner --skill edge-case-generationgit clone --depth 1 https://github.com/vladkesler/initrunnerWrote 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/vladkesler/initrunner/edge-case-generation)<a href="https://agentmods.dev/skills/vladkesler/initrunner/edge-case-generation"><img src="https://agentmods.dev/badge/skills/vladkesler/initrunner/edge-case-generation.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 5.1 | $0.00025 | $0.00622 |
| Opus 5 | $0.00013 | $0.00311 |
| Sonnet 5 | $0.00005 | $0.00124 |
| Haiku 4.5 | $0.00003 | $0.00062 |
Grade A, and why
edge-case-generation 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 6d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Systematic edge-case generation for thorough test coverage.
When to activate
Use this skill when generating tests for any function or module -- always consider edge cases alongside the happy path.
Boundary values
- Min and max integers (0, -1,
sys.maxsize,Number.MAX_SAFE_INTEGER). - Empty string
"", single-character string"a", very long strings. - Empty collections:
[],{},set(). - Zero, negative numbers, very large numbers.
- Single-element collections -- many off-by-one bugs surface here.
- Boundary of valid ranges: if a function accepts 1--100, test 0, 1, 100, and 101.
Null/None inputs
None(Python) ornull/undefined(JavaScript) for every parameter that could receive them.- Missing dictionary or object keys.
nullvalues inside JSON payloads.- Optional parameters omitted vs explicitly set to None/null.
Type edge cases
- Wrong types passed to loosely-typed functions (string where int expected).
- Unicode strings with emoji, RTL characters, zero-width joiners.
- Special characters: newlines, tabs, null bytes, path separators.
NaN,Infinity,-Infinityfor numeric inputs.- Very long strings (10k+ characters) to surface truncation or memory bugs.
Error paths
- Invalid arguments that should raise/throw.
- File not found, permission denied, directory instead of file.
- Network timeout, connection refused, DNS resolution failure.
- Malformed input: invalid JSON, broken XML, truncated data.
- Division by zero, integer overflow.
Concurrency
- Race conditions when two calls happen simultaneously (if applicable).
- Concurrent reads and writes to shared state.
- Reentrant calls -- calling a function while it is already executing.
Methodology
For each function parameter:
- List the valid range.
- Test the first valid value, the last valid value, and one value just outside each boundary.
For each branch in the function:
- Ensure at least one test exercises that branch.
For each exception or error the function can raise:
- Write a test that triggers it and verifies both the type and the message.
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.
- 6d ago First seen · 82 lines · 25 tokens per session scan A 8ec6b51e9ae4
edge-case-generation is a skill published in the GitHub repository vladkesler/initrunner (41 stars, last pushed 5d ago), licensed Apache-2.0. It adds 25 tokens to every session and 622 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
Vizra ADK Tool Creation
Build custom tools for Vizra ADK agents - includes patterns for database, API, file, and email tools.
Vizra ADK Evaluation Framework
Test and evaluate AI agents with automated evaluations, assertions, and LLM-as-a-Judge patterns.
Vizra ADK Memory System
Implement persistent memory, session context, and vector memory (RAG) for AI agents.
Vizra ADK Agent Creation
Create AI agents with Vizra ADK - includes patterns for customer service, data analysis, and content generation agents.
Vizra ADK Workflows
Orchestrate complex multi-agent workflows - sequential, parallel, conditional, and loop patterns.
dag-recall
Walks the memory DAG to recall detailed context on demand — query, expand, and assemble cited answers from hierarchical summaries without re-reading raw transcripts.