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 skills/ozmasterai/torus-framework/sprintnpx skills add OZmasterAI/Torus-Framework --skill sprintgit clone --depth 1 https://github.com/OZmasterAI/Torus-FrameworkWhat 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 | $0.00522 |
| Opus 5 | $0.00000 | $0.00261 |
| Sonnet 5 | $0.00000 | $0.00104 |
| Haiku 4.5 | $0.00000 | $0.00052 |
Grade A, and why
sprint 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 2d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sprint — Multi-Agent Self-Improvement Sprint
When to use
When user says "sprint", "self-improve sprint", "autonomous improvement", "launch improvement swarm", or wants to run a coordinated multi-agent improvement session.
Commands
/sprint— Full sprint with research + build + test phases/sprint research— Research-only phase (no code changes)/sprint build— Build-only phase (assumes research done)/sprint $ARGUMENTS— Focus on specific area (e.g., "gates", "skills", "memory")
Flow
Phase 1: ASSESS (2 min)
- Run
/benchmark --quickto capture baseline metrics - Read LIVE_STATE.json for current state
- Search memory for previous sprint results
- Identify top 5 improvement opportunities
Phase 2: RESEARCH (5 min)
Launch research swarm (3-5 haiku agents in parallel):
- Agent 1: Search GitHub for Claude Code frameworks
- Agent 2: Search for self-improving agent patterns
- Agent 3: Search for specific area improvements (from $ARGUMENTS)
- Collect results, save to memory
Phase 3: PLAN (2 min)
- Synthesize research findings
- Create prioritized task list using TaskCreate
- Score each task: Impact (40%) + Effort (30%) + Risk (20%) + Novelty (10%)
- Select top 5-7 tasks for implementation
Phase 4: BUILD (10 min)
Launch builder team (3-5 sonnet agents):
- Create agent team with TeamCreate
- Assign tasks to team members
- Monitor progress via TaskList
- Handle blocking issues
Phase 5: VERIFY (3 min)
- Run full test suite
- Compare metrics against Phase 1 baseline
- Fix any regressions
Phase 6: REPORT (1 min)
- Generate sprint report with
/report sprint - Save comprehensive results to memory
- Update LIVE_STATE.json and ARCHITECTURE.md
- Git commit all changes
Rules
- NEVER exceed 7 concurrent agents (resource limit)
- Research agents use haiku model, builders use sonnet
- Always capture baseline BEFORE making changes
- Stop after 2 consecutive test regressions (circuit breaker)
- Save all research and decisions to memory
- Maximum sprint duration: 25 minutes
- Update LIVE_STATE.json at each phase transition
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.
- 2d ago First seen · 61 lines · 0 tokens per session scan A db721948cce6
sprint is a skill published in the GitHub repository OZmasterAI/Torus-Framework (5 stars, last pushed 3mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 522 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…