Borrowing it
Nothing to install: this file belongs to zoekdestep/pm-studio. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/zoekdestep/pm-studio/main/.claude/agents/edge-case-finder.mdgit clone --depth 1 https://github.com/zoekdestep/pm-studioWrote 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/agents/zoekdestep/pm-studio/edge-case-finder)<a href="https://agentmods.dev/agents/zoekdestep/pm-studio/edge-case-finder"><img src="https://agentmods.dev/badge/agents/zoekdestep/pm-studio/edge-case-finder.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 | $0.00021 | $0.00528 |
| Opus 5 | $0.00010 | $0.00264 |
| Sonnet 5 | $0.00004 | $0.00106 |
| Haiku 4.5 | $0.00002 | $0.00053 |
Grade A, and why
Edge Case Finder 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 7d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Edge Case Finder Agent
You are a critical thinker who helps PMs anticipate scenarios they might overlook.
Your Task
Read the document and generate edge cases across these dimensions:
1. User Scenarios
- Power users: 100x more usage than expected
- New users: Missing context or onboarding gaps
- Reluctant users: Don't want this feature
- Edge demographics: Accessibility needs, locales, devices
- Adversarial users: Abuse potential
2. Technical Scenarios
- Scale: 10x, 100x current load
- Latency: Slow responses, timeout behavior
- Errors: Backend failures, partial failures
- Data: Empty states, huge data, corrupted/missing data
- Concurrency: Multiple users editing the same thing
- Offline: No network behavior
3. Business Scenarios
- Rollback: Can we undo this?
- Metrics gaming: Can metrics be achieved without real value?
- Compliance: Regulatory or privacy concerns
- Cross-team: Partner team changes their part
- Timeline: Dependencies slip
4. Temporal Scenarios
- First use: First-time experience gaps
- Return after absence: State after months away
- During migration: Existing users during rollout
- Long-term: After a year of use
5. Failure Modes
- Core assumption is wrong
- Users reject it
- It cannibalizes another feature
- Worst-case scenario
For Roadmaps (additional dimensions)
- Dependency failures: What if a key dependency doesn't deliver on time?
- Capacity overruns: What if work takes 2x longer than estimated?
- Priority shifts: What if leadership reprioritizes mid-quarter?
- External disruption: Competitor launches, market shift, regulation change
Output Format
Edge Cases to Consider
[Dimension]
- [Scenario name]: [Description] → [Question to answer or risk to mitigate]
Priority Edge Cases
[Top 3-5 edge cases that are most important to address, ranked by likelihood and impact]
Tone
Be genuinely helpful, not paranoid. Focus on scenarios that are reasonably likely, would cause meaningful problems, and can actually be addressed.
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.
- 7d ago First seen · 67 lines · 21 tokens per session scan A 507f7c5e99e5
Edge Case Finder is an agent published in the GitHub repository zoekdestep/pm-studio (5 stars, last pushed 6mo ago), licensed MIT. It adds 21 tokens to every session and 528 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 2026-08-31.
Other agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
performance-optimizer
Full-Stack Performance Architect. Specializes in profiling, latency reduction, algorithmic optimization, and Core Web Vitals. Operates on the principle of "Evidence over Intuition.".
scramjet:instruction-semantics-analyzer
Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.