Assess and adjust to Anthropic's June 15 2026 Agent SDK credit billing change. Use when the user wants to understand, measure, or reduce Claude / Claude Code token spend; asks about the "Agent SDK credit", "programmatic credit", "interactive vs programmatic" usage, the "$20/$100/$200 credit", caching to save money, model routing for cost, or estimating their bill impact after June 15 2026. Ingests their own usage history, classifies interactive vs programmatic burn by system, models the credit impact for their plan, finds caching wins, and proposes routing/workflow changes — then offers to implement.
How this skill is triggered — by the user, by Claude, or both
Slash command
/burn-safe-token-ledger:burn-safe-token-ledgerThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
A portable workflow for surviving Anthropic's **June 15, 2026** billing change with your
assets/credit-panel.htmlevals/README.mdevals/cases.jsonlexamples/personal-config.example.jsonexamples/sample-usage.jsonlexamples/uplift-router.reference.pyreferences/billing-policy-2026-06-15.mdreferences/caching-playbook.mdreferences/cost-model.mdreferences/routing-strategies.mdreferences/workflow-upgrades.mdscripts/analyze_caching.pyscripts/classify_burn.pyscripts/estimate_credit_impact.pyscripts/ingest_usage.pyscripts/prices.pyA portable workflow for surviving Anthropic's June 15, 2026 billing change with your bill unchanged. It measures where your Claude tokens actually go, separates the spend that moved to the new metered credit from the spend that didn't, projects the cost impact for your specific plan from your own history, and turns that into concrete caching and routing fixes.
Token-burn dashboard concept credited to Nate B. Jones (June 2026). See
CREDITS.md.
Trigger on any of: "how does June 15 affect me", "Agent SDK credit", "programmatic vs interactive", "am I going to get a bill now", "reduce my Claude spend", "should I move to an API key", "make caching pay off", "smart model routing", "what's my burn".
Interactive Claude usage (you driving a Claude Code session, Cowork, web/desktop/mobile) stays on your subscription limits — unchanged. Programmatic usage (Agent SDK,
claude -p, Claude Code GitHub Actions, third‑party SDK tools) now draws from a separate monthly Agent SDK credit, metered at full API rates, with a hard stop when exhausted unless you enable extra usage.
The deciding signal is authentication, not the task:
| How the call authenticates | Where it bills after June 15 |
|---|---|
| Your Claude subscription via OAuth, running the real Claude Code agent loop interactively | Subscription limits (no change) |
ANTHROPIC_API_KEY / the Agent SDK / claude -p / Claude Code GitHub Actions | New Agent SDK credit, then API‑rate overage or hard stop |
| A third‑party API key (e.g. OpenRouter) | Already pay‑as‑you‑go — unaffected |
Full policy detail and figures: references/billing-policy-2026-06-15.md.
Ask the user (or read personal-config.json): their plan (Pro / Max 5x / Max 20x / Team /
Enterprise), whether "extra usage" is enabled, and the default model. These set the credit
ceiling and per‑token prices. Never guess the plan — the credit ceiling depends on it.
Point the skill at their real usage sources. The canonical inputs are Claude Code session
transcripts (~/.claude/projects/**/*.jsonl) for interactive burn, plus any logs from
headless jobs (Agent SDK apps, claude -p scripts, GitHub Actions, cron/launchd jobs).
python3 scripts/ingest_usage.py --config personal-config.json --out usage.normalized.jsonl
ingest_usage.py reads each configured source, tags every turn with a class
(interactive | programmatic) and a system label, and emits one normalized record per
API turn. Sources and their classification live in personal-config.json — see
examples/personal-config.example.json. If you cannot prove a source is interactive, default
it to programmatic (fail safe toward the metered pool).
python3 scripts/classify_burn.py usage.normalized.jsonl
Outputs total tokens and dollar cost split by class and by system, so you can see exactly how much of your spend just became metered and which automation is responsible. This is the attribution Nate's dashboard concept makes visible — extended here to the interactive vs programmatic axis that June 15 introduced.
python3 scripts/estimate_credit_impact.py usage.normalized.jsonl --plan max20x
Takes the programmatic slice, prices it at API rates for the configured model, projects to
a full month, and compares against the plan's credit ceiling ($20 / $100 / $200). Reports:
projected monthly programmatic cost, credit headroom or overage, and the break‑even number of
runs. Always present this as a range (low/expected/high) anchored to their measured cache
hit rate — see references/cost-model.md.
python3 scripts/analyze_caching.py usage.normalized.jsonl
Cache reads cost ~0.1× input price; a cache write costs ~1.25×. This script reports current
cache hit rate, dollars already saved, and dollars still recoverable if stable prefixes were
cached. Caching is now a direct dollar lever on the programmatic pool. Playbook:
references/caching-playbook.md.
Map findings to concrete moves (descriptions in references/routing-strategies.md and
references/workflow-upgrades.md):
claude -p on the subscription.Do not auto‑apply. Summarize the 3–5 highest‑value changes with their estimated monthly savings, then offer to implement each against the user's actual system (wire up the router, add cache breakpoints, add the credit panel to their dashboard, gate the Actions). Implement only what they accept.
This skill is built to be re‑run. Use the bundled /burn-audit command on an interval:
/loop 1d /burn-audit re‑ingests, re‑classifies, and flags drift (e.g. a new cron job quietly
eating the credit). See commands/burn-audit.md.
All user‑specific paths, plan, and system labels live in personal-config.json, which is
gitignored. The repo ships only examples/personal-config.example.json. Never commit a
user's real paths, tool names, or usage data.
Prices and policy change. Treat references/cost-model.md (prices) and
references/billing-policy-2026-06-15.md (policy) as the single sources of truth, and run the
evals/ cases after any edit. See MAINTENANCE.md.
Guides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.
npx claudepluginhub emergentcap/burn-safe-token-ledger --plugin burn-safe-token-ledger