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 skills add gabriele-mastrapasqua/codex-lean-team --skill measured-performancegit clone --depth 1 https://github.com/gabriele-mastrapasqua/codex-lean-teamWrote 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/skills/gabriele-mastrapasqua/codex-lean-team/measured-performance)<a href="https://agentmods.dev/skills/gabriele-mastrapasqua/codex-lean-team/measured-performance"><img src="https://agentmods.dev/badge/skills/gabriele-mastrapasqua/codex-lean-team/measured-performance/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/skills/gabriele-mastrapasqua/codex-lean-team/measured-performance"><img src="https://agentmods.dev/badge/skills/gabriele-mastrapasqua/codex-lean-team/measured-performance.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 | $0.00033 | $0.00178 |
| Opus 5 | $0.00016 | $0.00089 |
| Sonnet 5 | $0.00007 | $0.00036 |
| Haiku 4.5 | $0.00003 | $0.00018 |
Grade A, and why
measured-performance 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 9d 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
Define the metric and baseline before changing code.
- Confirm workload, hardware/runtime, warmup, sample count, and correctness criteria.
- Profile or isolate the hot path.
- Choose the smallest plausible optimization.
- Measure before and after using the same method.
- Check correctness, variance, memory, and tail latency.
- Reject changes whose improvement is within noise or whose complexity is not justified.
For C/C++/Rust/CUDA/Metal, also check vectorization, locality, transfers, synchronization, alignment, aliasing, and numerical drift. For Go/Python/TypeScript, adapt to GC, event loops, allocation behavior, I/O, and runtime tooling.
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.
- 9d ago First seen · 16 lines · 33 tokens per session scan A 4e26363194ae
measured-performance is a skill published in the GitHub repository gabriele-mastrapasqua/codex-lean-team (3 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 178 once invoked, about $0.0002 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 skills, from other repositories
openlore-debug
Debug with OpenLore structural context, an explicit root-cause hypothesis, and RED/GREEN verification. Use when a bug, failure, or regression needs diagnosis and repair.
openlore-analyze-codebase
Run a full static OpenLore analysis and summarize architecture, call graph, refactoring issues, and duplicate code. Use when asked to analyze, map, or assess a codebase without LLM inference.
bug-detective
This skill should be used when the user asks to "debug this", "fix this error", "investigate this bug", "troubleshoot this issue", "find the problem", "something is broken", "this isn't working", "why is this failing", or reports errors/exceptions/bugs. Provides systematic debugging workflow and common error patterns.
tfx-find
A codebase search tool for quickly locating files, functions, classes, variables, text, and project structure. A codebase is the collection of source files that make up a software project.
do-it-code-quality
Use when designing, changing, or debugging code to locate causal ownership and close the affected behavior.
maintain-codex-wiki
Maintain a review-first Markdown knowledge base for Codex practices with source provenance, engineering capture, citation-aware queries, explicit archive and promotion, and deterministic linting. Use when asked to capture a durable engineering lesson, ingest Codex research, query or archive what the repository knows…