Tutti is a real-time collaboration space where people can work alongside multiple AI agents, including by sharing rooms, editing together, and borrowing agents. It is intended for users who want human-agent or multi-agent collaboration across devices, with open-source and VM versions available. The catalogue entries provide skills and instructions for working with Tutti.
Borrowing it
Nothing to install: this file belongs to tutti-os/tutti. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tutti-os/tutti/main/.codex/skills/analyze-performance-traces/SKILL.mdgit clone --depth 1 https://github.com/tutti-os/tuttiWrote 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/tutti-os/tutti/analyze-performance-traces)<a href="https://agentmods.dev/skills/tutti-os/tutti/analyze-performance-traces"><img src="https://agentmods.dev/badge/skills/tutti-os/tutti/analyze-performance-traces/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/tutti-os/tutti/analyze-performance-traces"><img src="https://agentmods.dev/badge/skills/tutti-os/tutti/analyze-performance-traces.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 8 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Prompt Injection · line 81 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00127 | $0.02562 |
| Opus 5.5 | $0.00051 | $0.01025 |
| Sonnet 5.5 | $0.00025 | $0.00512 |
| Haiku 4.5 | $0.00013 | $0.00256 |
Grade A, and why
analyze-performance-traces 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze Performance Traces
End with an evidence chain from trigger to exact source. Fix the earliest proven cause. Never turn an API name or an inclusive duration into a causal claim without checking execution context.
Choose the evidence mode
State which mode applies before making findings:
- Trace-backed: a trace is supplied or discoverable. Durations, processes, threads, and event ordering may be reported from it.
- Reported-finding audit: the user supplies durations or a chain but not the artifact. Treat those details as leads. Confirm current source paths and trigger conditions; label the durations, thread, and invalidation scope unverified.
- Source-only: no trace-derived lead exists. Report hypotheses, not measured bottlenecks.
Do not block a reported-finding audit merely because the original trace file is absent. If the user asks for safe implementation after the source chain is proven, proceed within authorization; require a comparable post-change trace before claiming millisecond or frame-rate improvement.
If neither a trace nor a concrete lead exists, ask for the smallest reproducible capture unless the user explicitly wants source-only analysis.
Start safely
-
Read repository instructions, nearest area instructions, relevant architecture docs, current diff, and validation policy. Record Git baseline before editing.
-
Discover trace artifacts without printing them wholesale. For each candidate:
ls -lh TRACE.json head -c 512 TRACE.json tail -c 512 TRACE.json -
Run the bundled bounded-memory summarizer:
node <skill-dir>/scripts/summarize-trace TRACE.json --top 40 --min-ms 16 -
Record trace revision/build, production versus development mode, profiling hooks, source maps, screenshots, React tracks, renderer count, and capture window. Separate profiler startup and instrumentation overhead from product work.
-
Prefer a repository-owned performance runner when it reproduces the same interaction. List scenarios first; a convenient but different scenario is not proof. In this repository, inspect
docs/conventions/testing.mdand usepnpm perf:agent-gui -- --list-scenarioswhen relevant.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 193 lines · 127 tokens per session scan A 103f509f4e92
analyze-performance-traces is a skill published in the GitHub repository tutti-os/tutti (3,872 stars, last pushed 21d ago), licensed Apache-2.0. It adds 127 tokens to every session and 2,562 once invoked, about $0.0005 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 skills, from other repositories
langsmith-tracing
LangSmith tracing and debugging setup for LLM applications. Configure observability, capture traces, and enable debugging for LangChain/LangGraph agents.
behavior-contract
Bug condition/postcondition formalization as testable Behavior Contracts. Defines invariants that must be preserved across fixes.
quality-hooks
Language-specific auto-lint/format/typecheck pipeline. Supports Python (ruff+pyright), TypeScript (prettier+eslint+tsc), Go (gofmt+golangci-lint). Auto-fix and convergence loops.
systematic-debugging
Structured debugging methodology using hypothesis-driven investigation, log analysis, and bisection to isolate and resolve defects.
opentelemetry-llm
OpenTelemetry instrumentation for LLM applications with distributed tracing.
debugging-patterns
Root cause analysis frameworks including log-first investigation, git bisect correlation, and pattern-based diagnosis with confidence scoring.