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 commands/design-and-deliver/claude-code-autoconfig/usage-reportgit clone --depth 1 https://github.com/design-and-deliver/claude-code-autoconfigWrote 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/commands/design-and-deliver/claude-code-autoconfig/usage-report)<a href="https://agentmods.dev/commands/design-and-deliver/claude-code-autoconfig/usage-report"><img src="https://agentmods.dev/badge/commands/design-and-deliver/claude-code-autoconfig/usage-report.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 | $0.00000 | $0.00609 |
| Opus 5 | $0.00000 | $0.00304 |
| Sonnet 5 | $0.00000 | $0.00122 |
| Haiku 4.5 | $0.00000 | $0.00061 |
Grade A, and why
usage-report 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Usage Report
Show the current session's usage report — tokens first (with the cache-read and per-model splits that make raw totals honest), the weighted $-equivalent beside them, the 5-hour cross-project rollup, and the plan/overage-billing line.
Renamed from /token-guard-report 2026-07-12 — the built-in /usage shows quota bars;
this shows where the usage went.
Step 1: Run the meter
Run via Bash (the session transcript lives at ~/.claude/projects/<project-slug>/<session_id>.jsonl — derive the path from the current project directory and session; if unsure, run without an argument and pass the transcript path only when known):
node .claude/hooks/token-guard.js --report "$HOME/.claude/projects/<project-slug>/<session_id>.jsonl"
Step 2: Display
Show the report output verbatim in a code block — do not summarize away the numbers. Add ONE line of interpretation at most (e.g. whether a fresh session is advisable given the live-context floor).
Notes for interpretation:
- The ALLOCATION block leads and is authoritative — those are Anthropic's own server-computed percentages (same source as the built-in /usage), fetched live with severity flags and reset times. Everything below it is supporting detail: WHERE the usage went. If it shows "unavailable", the estimate lines below are calibrated guesses, marked "≈ ... (estimate)".
- Tokens lead; dollars are API-list-price equivalents. On a subscription they proxy for rate-limit consumption, not billing — and the final
Plan:line says which applies (the overage-OFF case means worst-case throttling, never a charge). - "live context" is re-read on EVERY turn — that is the per-turn floor cost of continuing this session.
- The session total INCLUDES subagent/workflow fleet transcripts (the
main $X + agents $Ysplit line) — fleets bill outside the main transcript and historically hid 63% of a session's spend. - Thresholds are configured in
.claude/cca.config.json→tokenGuard(contextWarnTokens,sessionWarnUSD,hardGateUSD,gateStepUSD, plus v2:fleetMeter,workflowConfirm,bombJumpTokens,bombGateWhenFat,idleWarnMinutes,windowBudgetUSD,planDetect).
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 · 36 lines · 0 tokens per session scan A e6e100040120
usage-report is a command published in the GitHub repository design-and-deliver/claude-code-autoconfig (2 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 609 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.