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/korbinjoe/teemai/render-performance-verificationnpx skills add korbinjoe/TeemAI --skill render-performance-verificationgit clone --depth 1 https://github.com/korbinjoe/TeemAIWrote 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/korbinjoe/teemai/render-performance-verification)<a href="https://agentmods.dev/skills/korbinjoe/teemai/render-performance-verification"><img src="https://agentmods.dev/badge/skills/korbinjoe/teemai/render-performance-verification.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 | $0.00038 | $0.00633 |
| Opus 5 | $0.00019 | $0.00316 |
| Sonnet 5 | $0.00008 | $0.00127 |
| Haiku 4.5 | $0.00004 | $0.00063 |
Grade A, and why
render-performance-verification 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 4d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Render Performance Verification
Use this skill after UI-impacting work where render speed, mission switching, terminal restoration, or route readiness could regress.
This skill also installs an automatic Stop hook. At the end of an agent turn,
the hook detects changed code files, fingerprints their current contents, and
runs npm run build:ui plus npm run perf:render:changed once for each new
fingerprint. Set TEEMAI_RENDER_PERF_AUTO=0 to disable it locally.
Trigger
Run this for changes under:
web/components/**web/hooks/useChat*,web/hooks/useAgent*,web/hooks/useWorkspace*web/layouts/**,web/pages/**,web/App.tsxweb/**/*.cssor theme/layout files- server/WebSocket/API behavior that changes UI rendering or live mission state
Workflow
-
Run the normal build gate unless it already passed in the same task:
npm run build:ui -
Run changed-scope render verification:
npm run perf:render:changed -
If a scenario fails, rerun the failing scenario with trace artifacts:
npm run perf:render -- --scenario <scenario-id> --trace --keep-artifacts -
Read
.perf/render/<run-id>/report.mdand inspect the first failing scenario'smetrics.json, screenshot, and trace path. -
Fix the regression and rerun the relevant scenario or
perf:render:changed.
Harness Self-Check
If the failure evidence points to the harness itself, treat it as a harness regression and fix it before trusting the result. Common signs:
- selector strict-mode errors or missing selectors after a UI label changed
- a metric that is known to include detached or garbage-collection-sensitive browser state
- a changed-file mapping that misses an obviously impacted surface
- a scenario that flakes while screenshots, console, network, and interaction metrics are otherwise healthy
Do not bypass the scenario or update baselines for these cases. Patch the
harness, add or update the focused test when practical, then rerun the failing
scenario and npm run perf:render:changed.
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.
- 4d ago First seen · 87 lines · 38 tokens per session scan A ace36b1dfed2
render-performance-verification is a skill published in the GitHub repository korbinjoe/TeemAI (2 stars, last pushed 2mo ago), licensed MIT. It adds 38 tokens to every session and 633 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 2026-08-31.
Other skills, from other repositories
importing-a-codebase
Use when the repo holds real source code but no specs: the existing-codebase branch of setting-up-a-project, normally reached via that dispatcher, directly only when the situation is unmistakable. Not for empty workspaces (starting-a-new-project) or feature work in a specced project (brainstorming).
starting-a-new-project
Use when the workspace is empty — no code yet — and the user brings a raw idea: the brand-new branch of setting-up-a-project, normally reached via that dispatcher, directly only when the situation is unmistakable. Not for features in an existing project — use brainstorming instead.
agent-spec-tool-first
CRITICAL: Use for agent-spec CLI tool workflow. Triggers on: agent-spec, contract, lifecycle, guard, verify, explain, stamp, checkpoint, plan, requirements, work-units, knowledge requirements, KLL, docs vs knowledge, spec verification, task contract, spec quality, lint spec, run log, "how to verify", "how to use…
agent-spec-authoring
CRITICAL: Use for writing and editing agent-spec .spec/.spec.md files. Triggers on: write spec, create spec, edit spec, new spec, spec authoring, task contract, .spec file, .spec.md file, BDD scenario, acceptance criteria, completion criteria, test selector, boundary, constraint, intent, decision, out of scope, "how…
agent-spec-estimate
CRITICAL: Use for estimating work effort from agent-spec Task Contracts. Triggers on: estimate, estimation, how long, work effort, round count, time estimate, scope, sizing, cost, budget, planning, sprint, capacity, "how many rounds", "how long will this take", "estimate this spec", 估算, 工作量, 多久, 时间估算, 预估, 工时, 规模…
agent-spec-intent-compiler
Use when converting PRD or issue prose into KLL requirements, running the intent compiler plan, or reverse-interviewing a human to resolve requirement ambiguity before task spec generation.