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/oreum-ai/smartstack/context-budgetnpx skills add oreum-ai/smartstack --skill context-budgetgit clone --depth 1 https://github.com/oreum-ai/smartstackWhat 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 | $0.00453 |
| Opus 5 | $0.00000 | $0.00227 |
| Sonnet 5 | $0.00000 | $0.00091 |
| Haiku 4.5 | $0.00000 | $0.00045 |
Grade A, and why
context-budget 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.
What it actually says
Skill: Context Budget
When to use
At the start of any task, and whenever you're about to read files to gather context. Keeps you from burning tokens by scanning the whole repo when a targeted read would do.
The principle
Context is a budget. Spend it on the few files that matter for the task, not on re-reading everything every session. SmartStack exists so you can load summaries instead of raw code.
Procedure
- Start from the index, not the filesystem. Read
ai-rules/context/file-map.mdto locate things instead of recursive directory listing. Readai-rules/context/project.mdfor what the project is and its current state. These answer most "where/what" questions. - Load only the rule(s) for the domain you're touching. UI task →
rules/frontend.md. DB task →rules/database.md. Don't load all rules for a one-line change. - Use memory by index. For "did we hit this before?", read
memory/errors/INDEX.mdand jump to the matching entry — don't read every past error. Same formemory/sessions/INDEX.md. - Open source files just-in-time. Read a file right before editing it, and read the specific function/section when the file is large (use a line range), not the whole thing.
- Prefer the data/API summaries.
context/data-model.mdandcontext/api-map.mdusually answer schema/endpoint questions without opening the code. - Don't paste large blobs into prompts. Reference the path; let the reader open it if needed.
Rules of thumb
- One focused task = a handful of files, not the repo.
- If you've read a summary, don't also read the full thing "to be safe."
- Keep your working notes short; let the memory files hold detail.
- If the task is big, split it — smaller scope reads fewer files and produces better output.
Output
When you start a task, briefly state which context files you loaded and why. Makes the budget visible.
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 · 33 lines · 0 tokens per session scan A 7c0a4b5ffabc
context-budget is a skill published in the GitHub repository oreum-ai/smartstack (5 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 453 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…