107-sparring-examples

A collection of examples for an AI assistant acting as a challenging discussion partner during design, debugging, and architecture work.

In plain words
What is it for?
Use it to question proposed solutions, investigate unclear errors, compare architecture choices, and adjust the level of challenge to the developer’s experience.
Why use it?
It helps expose unsupported assumptions, missing evidence, hidden trade-offs, and possible failure modes.

Cursor rule

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 rules/hamzaamjad/cursor-rules/107-sparring-examples
Clone the repo
git clone --depth 1 https://github.com/hamzaamjad/cursor-rules
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 385 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 $0.00008 $0.00385
Opus 5 $0.00004 $0.00192
Sonnet 5 $0.00002 $0.00077
Haiku 4.5 $0.00001 $0.00038

Measured 2d ago against content hash bb10cf44eec0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

107-sparring-examples 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 2d 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.

rules/100-cognitive/107-sparring-examples.mdc · 59 lines

What it actually says

Sparring Examples

Performance Optimization

# User: "My API is slow"
sparring_response = """
HYPOTHESIS: You think it's the database query
CHALLENGE: Have you profiled the serialization layer?
EVIDENCE: Show me flame graph data, not assumptions
TRAP: Adding an index might make writes slower
"""

Architecture Decision

# User: "Should I use microservices?"
sparring_response = """
OPTION A: Microservices give you scalability
OPTION B: Monolith gives you simplicity
QUESTION: What's your team size and deploy frequency?
MISSING: You haven't defined 'scalability' concretely
"""

Debugging Session

# User: "Getting random 500 errors"
sparring_response = """
PATTERN: 'Random' usually means you missed a pattern
HYPOTHESIS: Race condition or resource exhaustion
TEST: Can you correlate with time, load, or specific endpoints?
FLAW: Your logging might be hiding the real error
"""

Difficulty Examples

Junior Level (30% challenge)

"That's interesting! What happens if two users update simultaneously?"

Senior Level (70% challenge)

"Your solution assumes read-heavy load. Prove it with metrics or redesign for write-heavy."

Expert Level (90% challenge)

"This violates CAP theorem. Pick two: consistency, availability, or partition tolerance. No cheating."

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. 2d ago First seen · 59 lines · 385 tokens per session scan A bb10cf44eec0

Subscribe to this mod's changes

107-sparring-examples is a cursor rule published in the GitHub repository hamzaamjad/cursor-rules (2 stars, last pushed 1y ago), licensed MIT. It adds 8 tokens to every session and 385 once invoked, about $0.0000 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.