examples: live ContextLevy demo (do not merge)

[nonlooped]

Summary

Permanent showcase PR for ContextLevy. Adds /examples/agent-debt-pr/ fixtures (lockfile, build output, agent config) so visitors can inspect a live PR comment, workflow check, and job summary.

Do not merge. Maintainers: rebase this branch onto main when the demo needs refreshing.

Reopened after git history rewrite invalidated PR #12.

Test plan

• ContextLevy workflow runs on this PR
• PR comment posted when thresholds exceeded

[contextlevy]

🤖 ContextLevy

This PR adds agent instruction changes, build artifacts, and lockfile churn — expect a noisy agent review. Agent instructions also changed.

Risk level: 🔴 High · ~20.1k estimated context tokens

Added	Finding
+1.3k	examples/agent-debt-pr/.agents/skills/onboarding/SKILL.md Agent instruction files are high-signal but add persistent context overhead.
+7.9k	examples/agent-debt-pr/dist/app.js Build artifacts are rarely useful agent context.
+10.7k	examples/agent-debt-pr/pnpm-lock.yaml Lockfiles add bulk context; agents often need dependency names but not every resolved URL.

Estimated worst-case input cost if read by an agent
Illustrative only — agents may not read every changed file. Not billing-grade.

Pricing profile	Est. input cost (±50%)
GPT-5.5	~$0.05–$0.15/session
Kimi K2.6	~$0.01–$0.03/session

Suggestions

• Commit lockfiles when your team policy requires reproducible installs — just expect higher context cost.
• Keep build output out of version control.
• Keep agent instructions concise and scoped to what agents must know.
• Consider excluding these paths from agent indexing (tool-agnostic):
• examples/agent-debt-pr/dist/app.js

Many tools honor .gitignore; others support dedicated ignore files such as .cursorignore.

Different models tokenize differently, and agents may not read every changed file. ContextLevy estimates context risk, not exact billing.

ContextLevy runs locally in CI and does not send code to an external API.