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/telus-labs/stagecraft/performance-budgetnpx skills add telus-labs/stagecraft --skill performance-budgetgit clone --depth 1 https://github.com/telus-labs/stagecraftWrote 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/telus-labs/stagecraft/performance-budget)<a href="https://agentmods.dev/skills/telus-labs/stagecraft/performance-budget"><img src="https://agentmods.dev/badge/skills/telus-labs/stagecraft/performance-budget.svg" alt="Measured on agentmods" 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 | $0.00081 | $0.02487 |
| Opus 5 | $0.00041 | $0.01243 |
| Sonnet 5 | $0.00016 | $0.00497 |
| Haiku 4.5 | $0.00008 | $0.00249 |
Grade A, and why
performance-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 6d 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 — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance budget
Use this skill at Stage 6e (after QA, on full / quick / hotfix tracks). Measures the three performance dimensions relevant to the change — Lighthouse Web Vitals, bundle size delta, and load-test throughput — and compares each against configured budgets.
When to use each check
| Check | Use when |
|---|---|
| Lighthouse | Frontend change touched a page or route (new component, redesigned flow, added asset loading) |
| Bundle size | Change adds/removes JS or CSS that is bundled (new import, removed dependency, asset optimization) |
| Load test | Change modifies an HTTP endpoint, adds a new API route, or changes a query/computation that runs on every request |
When to skip entirely: If the change is purely backend with no HTTP surface change, doc-only, or infra config with no throughput impact, set skipped_reason and status PASS.
Budget thresholds
Look for budgets in this order:
performance.budget.jsonat the project root (preferred — machine-readable, shareable).devteam/config.ymlunderperformance.budgets.*- These defaults when no config exists:
| Metric | Default budget |
|---|---|
| Lighthouse score | ≥ 0.80 (80/100) |
| LCP | ≤ 2500ms |
| INP | ≤ 200ms |
| CLS | ≤ 0.1 |
| Bundle total | — (warn only; no hard limit without explicit config) |
| Bundle delta | ≤ 50KB per PR |
| Load p95 | ≤ 200ms |
| Load error rate | ≤ 1% |
If performance.budget.json is absent, record that in the report and note which defaults were applied.
Procedure
1. Scope the change
Read pipeline/brief.md, pipeline/design-spec.md, and pipeline/test-report.md. Identify:
- Which pages or routes were touched (for Lighthouse)
- Whether new assets / imports were added (for bundle)
- Which endpoints were modified (for load test)
Based on the scope, decide which of the three checks to run. Record what you chose (and why you skipped any check) in the report.
2. Read the budgets
# Check for project budget file
cat performance.budget.json 2>/dev/null || echo "No performance.budget.json found"
# Check config
cat .devteam/config.yml | grep -A 20 "performance:" || echo "No config section"
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.
- 6d ago First seen · 253 lines · 81 tokens per session scan A 3f0b6ad76161
performance-budget is a skill published in the GitHub repository telus-labs/stagecraft (6 stars, last pushed yesterday), licensed MIT. It adds 81 tokens to every session and 2,487 once invoked, about $0.0004 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
semantix
Install and use the semantix memory kernel as a middleware in your agent: extract user preferences / workflows / experience from past sessions, retrieve and inject them on demand. One binary + your agent's own tools.
semantix-guide
Troubleshoot and configure Semantix capabilities: Skills (project/custom/global/builtin priority, discovery dirs), Commands (override order, /dir:file naming), Hooks (11 events, automatic project loading, matchers, timeouts), MCP (semantix-agent.toml + .mcp.json + plugin packages, autostart), plugin packages…
intuitive-tests
Use this skill whenever the user asks about unit test best practices, test organization, flat test suites, redundant tests, test refactors, pytest/JUnit/Jest/xUnit layout, test taxonomy, flaky tests, coverage quality, fixtures, mocks, parametrization, pruning existing UTs, or "which tests are worth keeping." It…
intuitive-flow
Stable execution/change router after an approved plan, preflight contract, or tiny concrete task. Refactor-shaped work delegates to intuitive-refactor, and durable work runs through staged planning, review, GSD handoff, implementation, cleanup, and verification while keeping plan ledgers and active capsules compact by…
intuitive-preflight
Turn a vague task, plan, issue, or "LGTM/go ahead" request into an approval-ready preflight contract before implementation starts. Use when the user wants prompt preflight, clearer scope, non-goals, context package, acceptance criteria, definition of done, verification, stop gates, the exact execution command, or…
intuitive-squash
Squash local GSD or agent-generated commit history into a clean, reviewable story while preserving important fixes. Use when the user asks to squash commits, clean git history, compress phase commits, prepare a branch before PR, compare aggressive vs moderate squash options, or preserve hotfix/security commits during…