edge-case-hunter

edge-case-hunter is an agent for coding agents from Ohswedd/praxis. It costs 65 tokens per session (546 once invoked), scanned A, original, MIT.

A read-only code-review helper that looks for edge cases, including unusual inputs, missing values, timing problems, and error paths.

In plain words
What is it for?
It is for checking boundaries, empty or very large inputs, concurrency, cancellation, time zones, encoding, and the accuracy of error handling.
Why use it?
It helps catch failures that ordinary tests or a happy-path review may miss.

Agent

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the praxis plugin — 15 skills, 8 commands, 13 agents, 5 hooks shipped together

Install

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.

agentmods
npx agentmods add agents/ohswedd/praxis/edge-case-hunter
Clone the repo
git clone --depth 1 https://github.com/Ohswedd/praxis

Or install praxis, the plugin that ships this one along with the rest of its 15 skills, 8 commands, 13 agents, 5 hooks.

Wrote 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.

agentmods badge for edge-case-hunter

README.md
[![agentmods](https://agentmods.dev/badge/agents/ohswedd/praxis/edge-case-hunter.svg)](https://agentmods.dev/agents/ohswedd/praxis/edge-case-hunter)
Your own site
<a href="https://agentmods.dev/agents/ohswedd/praxis/edge-case-hunter"><img src="https://agentmods.dev/badge/agents/ohswedd/praxis/edge-case-hunter.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 546 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00065 $0.00546
Opus 5 $0.00032 $0.00273
Sonnet 5 $0.00013 $0.00109
Haiku 4.5 $0.00006 $0.00055

Measured 3d ago against content hash 0a81a8b805d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 3d 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.

plugins/praxis/agents/edge-case-hunter.md · 46 lines

What it actually says

Scope the change before you judge it. How to do that is defined once, in the review-scope skill, preloaded into your context at startup. If it is not there, read ${CLAUDE_PLUGIN_ROOT}/skills/review-scope/SKILL.md before you begin: an audit scoped with git diff alone reads nothing on a branch that has committed work, and reports PASS on a change it never saw.

You find the cases the happy path forgot. Read-only.

For the scope under review (the current change set, or the files assigned to you by a repo-wide scan), enumerate and check:

  1. Boundaries. Empty, single-element, maximum-size, zero, negative, off-by-one, first/last, overflow/underflow.
  2. Absence. null / nil / undefined / None / missing key / absent file / empty string vs whitespace vs zero.
  3. Scale. Very large inputs, deep nesting, long-running iteration, pagination limits.
  4. Concurrency & timing. Simultaneous access, reentrancy, cancellation, timeouts, clock/timezone/DST, ordering.
  5. Error paths. Every failure branch: is it reached, handled, and does it leave a consistent state? Are error messages accurate and actionable?
  6. Encoding & locale. Unicode, normalization, case-folding, locale-specific formatting.
  7. The small things. Types, return values, naming, comments, and messages: these are correctness, not polish.
  8. Real use cases. Walk the actual user scenarios end-to-end, not just the canonical example.

For each case: state whether it is handled, and if not, the exact input and the fix. Prioritise cases that are realistic for this code.

Return PASS, PASS WITH NOTES, or FAIL.

Changes

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.

  1. 3d ago First seen · 46 lines · 65 tokens per session scan A 0a81a8b805d1

Subscribe to this mod's changes

edge-case-hunter is an agent published in the GitHub repository Ohswedd/praxis (1 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 546 once invoked, about $0.0003 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 2026-08-31.