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/poteto/noodle/reflectnpx skills add poteto/noodle --skill reflectgit clone --depth 1 https://github.com/poteto/noodleWhat 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 | $0.00040 | $0.00657 |
| Opus 5 | $0.00020 | $0.00329 |
| Sonnet 5 | $0.00008 | $0.00131 |
| Haiku 4.5 | $0.00004 | $0.00066 |
Grade A, and why
reflect 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reflect
Review the conversation and persist learnings — to brain/, to skill files, or as structural enforcement.
Process
Use Tasks to track progress (TaskCreate per step, TaskUpdate to in_progress/completed).
- Read
brain/index.mdto understand what notes already exist - Scan the conversation for:
- Mistakes made and corrections received
- User preferences and workflow patterns
- Codebase knowledge gained (architecture, gotchas, patterns)
- Tool/library quirks discovered
- Decisions made and their rationale
- Friction in skill execution, orchestration, or delegation
- Repeated manual steps that could be automated or encoded
- Skip anything trivial or already captured in existing brain files
- Route each learning to the right destination (see Routing below)
- Update
brain/index.mdif any brain files were added or removed
Routing
Not everything belongs in the brain. Route each learning to where it will have the most impact.
Structural enforcement check
Before routing a learning to brain/, ask: can this be a lint rule, script, metadata flag, or runtime check? If yes, encode it structurally and skip the brain note. See brain/principles/encode-lessons-in-structure.md.
Brain files (brain/)
Codebase knowledge, delegation principles, gotchas — anything that informs future sessions. This is the default destination. Use the brain skill for writing conventions.
- One topic per file. File name = topic slug.
- Group in directories with index files using
[[wikilinks]]. - No inlined content in index files.
Skill improvements (.agents/skills/<skill>/)
If a learning is about how a specific skill works — its process, prompts, or edge cases — update the skill directly. Use the skill-creator skill for guidelines on effective skill content.
Orchestration workflow improvements
If the session revealed systemic orchestration issues, route to:
- Brain principle (new delegation heuristic) →
brain/delegation/ - Skill mechanics change (monitoring loop, review step) → relevant skill file
- New skill opportunity (recurring workflow that could be encoded) → note in summary for the user
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 · 71 lines · 40 tokens per session scan A d414a01130c8
reflect is a skill published in the GitHub repository poteto/noodle (267 stars, last pushed 5mo ago), licensed MIT. It adds 40 tokens to every session and 657 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 2026-08-30.
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…