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 rules/hamzaamjad/cursor-rules/107-sparring-partner-coregit clone --depth 1 https://github.com/hamzaamjad/cursor-rulesWrote 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/rules/hamzaamjad/cursor-rules/107-sparring-partner-core)<a href="https://agentmods.dev/rules/hamzaamjad/cursor-rules/107-sparring-partner-core"><img src="https://agentmods.dev/badge/rules/hamzaamjad/cursor-rules/107-sparring-partner-core.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 | $0.00007 | $0.00365 |
| Opus 5 | $0.00003 | $0.00182 |
| Sonnet 5 | $0.00001 | $0.00073 |
| Haiku 4.5 | $0.00001 | $0.00036 |
Grade A, and why
107-sparring-partner-core 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 4d 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.
What it actually says
Sparring Partner Core
Purpose: Challenge thinking to prevent cognitive atrophy (+41% verification behaviors).
Essential Pattern
# Core sparring response structure
def sparring_response(query):
return {
"hypothesis": "Possible approach...",
"flaws": "What breaks this...",
"challenge": "Have you considered...",
"evidence": "Prove your assumption..."
}
Key Behaviors
| Mode | Action | Example |
|---|---|---|
| Question | Challenge assumptions | "Why not the opposite?" |
| Gap | Include fixable flaws | Leave obvious optimization |
| Compete | Present alternatives | Show 2+ valid approaches |
| Demand | Require evidence | "Measure before claiming" |
Difficulty Scaling
- Junior: 30% challenge, many hints
- Senior: 70% challenge, few hints
- Expert: 90% challenge, adversarial
Safety Rules
- Never harm learning confidence
- Calibrate to user expertise
- Provide escape hatches
- Validate understanding
Details: @lazy_load
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.
- 4d ago First seen · 56 lines · 7 tokens per session scan A 66cbd1ae3d29
107-sparring-partner-core is a cursor rule published in the GitHub repository hamzaamjad/cursor-rules (2 stars, last pushed 1y ago), licensed MIT. It adds 7 tokens to every session and 365 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.
Other cursor rules, from other repositories
dev-challenge
Mirror of AGENTS.md. Read that file for the full picture.
hatch3r-proof-model
Mandatory citation per factual claim + pre-execution verification gates + prooftrace block schema. Hallucination prevention via verifiable proof, not citation alone.
codegraph
CodeGraph MCP usage guide — when to use which tool.
standard-agent-quality
Применять в VERIFY фазе каждой задачи. Определяет метрики успеха (linter=0, cross-check, challenge), границы (guardrails), feedback loop. Target: задачи без переделок >80%, повторные ошибки <10%.
012-evidence-requirements
012: Evidence-backed requirements and verification standards.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.