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 skills add codebygarv/Ai-skills --skill edge-case-huntergit clone --depth 1 https://github.com/codebygarv/Ai-skillsWrote 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/codebygarv/ai-skills/edge-case-hunter)<a href="https://agentmods.dev/skills/codebygarv/ai-skills/edge-case-hunter"><img src="https://agentmods.dev/badge/skills/codebygarv/ai-skills/edge-case-hunter/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/codebygarv/ai-skills/edge-case-hunter"><img src="https://agentmods.dev/badge/skills/codebygarv/ai-skills/edge-case-hunter.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00039 | $0.00544 |
| Opus 5.5 | $0.00016 | $0.00218 |
| Sonnet 5.5 | $0.00008 | $0.00109 |
| Haiku 4.5 | $0.00004 | $0.00054 |
Grade A, and why
edge-case-hunter 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 1mo 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Enumerate the edge cases a given piece of functionality is likely to mishandle — unusual input, boundary values, empty/missing states, and unexpected user behavior — the class of case that a "does it work for the normal case" pass typically skips.
When to Use
- Before shipping something that handles user input or external data.
- After writing normal-case tests, to find what's still missing.
- Specifically want edge cases enumerated, separate from a general bug hunt (see Bug Hunter for defects in existing code; this skill is about enumerating cases to consider, whether or not code exists yet).
What to Analyze
- Boundary values — zero, negative, empty string/array/object, exactly at a limit (min/max), one below/above a limit.
- Empty & missing states — no data yet (first-time user), data deleted mid-session, a required relationship missing (e.g. a comment whose author was deleted).
- Unexpected user behavior — double-submitting a form, navigating away mid-action, using browser back/forward against app state, extremely fast repeated actions.
- Unusual but valid input — very long strings, unicode/emoji, whitespace-only input, numbers as strings, timezone edge cases (midnight, DST transitions, leap years/seconds).
- Concurrent/simultaneous actions — two actors acting on the same resource at once, the same actor acting on two devices/tabs at once.
- Degraded conditions — slow network, partial data load, a dependency being down or timing out.
Output Format
- A checklist grouped by category (Boundary Values, Empty/Missing States, Unexpected Behavior, Unusual Input, Concurrency, Degraded Conditions).
- Each item: the specific case, why it's plausible (not just theoretically possible), and what currently happens (if known/inferable) or what should happen.
- Prioritize cases realistic for this specific feature over generic edge cases that don't actually apply to it.
Avoid
- Generating a generic checklist that doesn't reflect what this specific feature actually does — every case should be plausible for the feature at hand.
- Treating truly impossible cases (violating a hard invariant enforced elsewhere) as if they need handling here too.
- Listing a case without saying why it matters or what should happen — a bare list of scenarios isn't actionable.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 36 lines · 39 tokens per session scan A 1dd08a237dbc
edge-case-hunter is a skill published in the GitHub repository codebygarv/Ai-skills (27 stars, last pushed 2mo ago), licensed MIT. It adds 39 tokens to every session and 544 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
debugging
Use when debugging bugs, test failures, or unexpected behavior. Triggers: 'why isn't this working', 'this doesn't work', 'X is broken', 'something's wrong', 'getting an error', 'exception in', 'stopped working', 'regression', 'crash', 'hang', 'flaky test', 'intermittent failure', or when user pastes a stack…
bun-cli
Bun CLI reference for package management, script running, type checking, testing, bundling, and compilation. Covers bun install/add/remove/update, bun run, bun check and --check, bun test, bun build, bunx, bun patch, bun audit fix, bun dedupe, bun prune, bun why, bun pm, bun repl, bunfig.toml, bun.lock, workspace…
git-ci
CI/CD status queries for GitHub Actions (gh) and GitLab CI (glab). Check pipeline status, failing jobs, workflow runs, job logs, and merge readiness. Use when checking CI status, debugging build failures, viewing job logs, watching pipeline progress, or configuring gh/glab CI read-only allowlists. Not for PR workflows…
staged-transformation-pipeline
Monolithic transformations are hard to test and debug.
ds-test
Universal test skill — generate, update, run, and fix tests for any stack. Use when writing, repairing, or running tests, or improving coverage.
ds-build
Plan executor — take an issue, a specs/{feature}/tasks.md, or a plain request and implement it unit by unit with a verify signal per unit, red-proven tests, budgeted backtracking, and a code-proven close. Use when the plan exists and the work is to be done, not planned.