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 commands/reliverse/experiments/improvements-with-benchmarksgit clone --depth 1 https://github.com/reliverse/experimentsWhat 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 | $0.00000 | $0.02348 |
| Opus 5 | $0.00000 | $0.01174 |
| Sonnet 5 | $0.00000 | $0.00470 |
| Haiku 4.5 | $0.00000 | $0.00235 |
Grade A, and why
improvements-with-benchmarks 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 yesterday.
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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Suggest and apply improvements with benchmarks
Purpose
This command guides the AI to improve a package library's performance using a systematic benchmarking approach. The goal is to ensure optimizations are measurable and don't introduce regressions.
Packages to Optimize
The following packages should be optimized in priority order (packages with older lastImproved timestamps should be prioritized):
| # | Package | Last Improved | Status | Notes |
|---|---|---|---|---|
| 0 | @reliverse/dler |
- | - | - |
| 1 | @reliverse/build |
- | - | - |
| 2 | @reliverse/bump |
- | - | - |
| 3 | @reliverse/config |
- | - | - |
| 4 | @reliverse/datetime |
- | - | - |
| 5 | @reliverse/helpers |
- | - | - |
| 6 | @reliverse/mapkit |
- | - | - |
| 7 | @reliverse/matcha |
- | - | - |
| 8 | @reliverse/pathkit |
- | - | - |
| 9 | @reliverse/publish |
- | - | - |
| 10 | @reliverse/relico |
- | - | - |
| 11 | @reliverse/relifso |
- | - | - |
| 12 | @reliverse/relinka |
- | - | - |
| 13 | rempts |
- | - | - |
| 14 | @reliverse/tsconfig |
- | - | - |
| 15 | @reliverse/typerso |
- | - | - |
Metadata Fields:
- Last Improved: Timestamp (CET timezone) when performance improvements were last completed (format:
YYYY-MM-DD HH:mm:ss) - Status: Current optimization status (
pending,in-progress,completed,skipped)in-progress: ⚠️ CRITICAL: If a package has statusin-progress, it means another AI agent is currently working on it. DO NOT select or work on packages with this status. Skip them and move to the next available package.
- Notes: Any relevant information about the package or optimization results
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.
- yesterday First seen · 209 lines · 0 tokens per session scan A 6e4ef3c925c6
improvements-with-benchmarks is a command published in the GitHub repository reliverse/experiments (118 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,348 tokens. 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 2026-09-01.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.