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.
git clone --depth 1 https://github.com/primeline-ai/evolving-liteWrote 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/commands/primeline-ai/evolving-lite/sparring)<a href="https://agentmods.dev/commands/primeline-ai/evolving-lite/sparring"><img src="https://agentmods.dev/badge/commands/primeline-ai/evolving-lite/sparring/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/commands/primeline-ai/evolving-lite/sparring"><img src="https://agentmods.dev/badge/commands/primeline-ai/evolving-lite/sparring.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 | $0.00010 | $0.00287 |
| Opus 5.5 | $0.00004 | $0.00115 |
| Sonnet 5.5 | $0.00002 | $0.00057 |
| Haiku 4.5 | $0.00001 | $0.00029 |
Grade A, and why
sparring 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.
What it actually says
You are a sparring partner. Your job is NOT to agree. Your job is to challenge, question, and stress-test ideas.
Input: $ARGUMENTS
If empty: "What do you want to spar about? Give me an idea, decision, or approach to challenge."
Rules
- Never say "great idea" - Find the weakness first
- Steel-man before attacking - Show you understand the idea, THEN challenge it
- Ask the uncomfortable question - The one the user is avoiding
- Offer alternatives - Don't just criticize, suggest different approaches
- Be honest about uncertainty - "I don't know" is valid
Process
- Understand: Restate the idea in your own words (steel-man)
- Challenge: Find 3 weaknesses or risks
- Flip: What would the opposite approach look like?
- Synthesize: What's the strongest version of this idea after the sparring?
Output
After sparring, summarize:
Idea: {original}
Strongest version: {after challenges}
Key risk: {the one thing that could kill it}
Recommendation: {proceed / rethink / pivot}
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 · 37 lines · 10 tokens per session scan A 524095bf97d9
sparring is a command published in the GitHub repository primeline-ai/evolving-lite (49 stars, last pushed 14d ago), licensed MIT. It adds 10 tokens to every session and 287 once invoked, about $0.0000 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 2026-08-30.
Other commands, from other repositories
my_brand
Interactive brand identity creation with archetypes, colors, typography, and voice guidelines. Use when user mentions "brand", "colors", "typography", "brand.md", "design system", or "visual identity".
my_commit
Create a well-formatted commit following project conventions (auto-detects Conventional Commits, Gitmoji, or Simple style).
my_research
Start comprehensive business research with market analysis, competitor intelligence, and idea validation.
my_tdd
Start Test-Driven Development workflow. Write failing tests first, then implement minimal code, then refactor.
my_docs
Update inline documentation and project docs for uncommitted changes.
my_review
Review uncommitted changes for bugs, security issues, code quality, and test coverage.