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.
git clone --depth 1 https://github.com/BFRKQSB7/balance-hudWrote 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/bfrkqsb7/balance-hud/debug)<a href="https://agentmods.dev/commands/bfrkqsb7/balance-hud/debug"><img src="https://agentmods.dev/badge/commands/bfrkqsb7/balance-hud/debug.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 | $0.00027 | $0.00987 |
| Opus 5 | $0.00014 | $0.00494 |
| Sonnet 5 | $0.00005 | $0.00197 |
| Haiku 4.5 | $0.00003 | $0.00099 |
Grade A, and why
debug scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagnose Balance HUD
Run the self-diagnostic that mirrors exactly what Claude Code invokes on every statusline refresh, then fix whatever it flags.
Step 1: Run diagnostics
node "${CLAUDE_CONFIG_DIR:-$HOME/.claude}/plugins/balance-hud/scripts/hud_debug.mjs"
The report covers:
| Section | What it verifies |
|---|---|
| Provider 分类 | official Anthropic / DeepSeek / local proxy (ccswitch) / relay |
isDeepSeekEnv |
whether the DeepSeek balance row should appear at all |
| statusLine 接线 | statusLine present in settings.json and its target file exists |
| 插件 | version + all required files present |
| HUD 配置 | config.json parses (else defaults) |
| 余额快照 | balance_usage.json freshness + whether it should display |
| 余额 daemon | auto_refresh running? stale pid file? |
| statusLine 看门狗 | fix_statusline --watch running + startup item present |
| 模拟渲染 | end-to-end render with a synthetic statusline stdin payload |
Step 2: Interpret ✗ (problem) lines
Fix each reported problem in order of impact:
-
statusLine.commandmissing —settings.jsonwas rewritten (e.g. by ccswitch) and the statusline was dropped, so Claude Code never invokes the HUD. Run the guard once:node "${CLAUDE_CONFIG_DIR:-$HOME/.claude}/plugins/balance-hud/scripts/fix_statusline.mjs"If the watchdog (
fix_statusline --watch) is not running either, it will recur. Start it (Windows startup item is at%USERPROFILE%\AppData\Roaming\Microsoft\Windows\Start Menu\Programs\Startup\balance-hud-statusline.vbs). -
statusLine target ✗ 不存在 — the command points at a file that no longer exists (e.g. plugin was reinstalled to a different path). Re-run
/balance-hud:setupor correctstatusLine.commandinsettings.json. -
模型显示角色名而非真实模型 — only relevant on third-party relays (OpenCode Go etc.). The HUD resolves the real model via
ANTHROPIC_DEFAULT_<ROLE>_MODEL_NAMEenv vars; if the report shows the role (claude-sonnet-4-6) instead of the real model, confirm the env mapping is set for that role and thatdist/stdin.jsresolveEnvModelAliasis present.
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 · 89 lines · 27 tokens per session scan A d9113d257bc8
debug is a command published in the GitHub repository BFRKQSB7/balance-hud (2 stars, last pushed 21d ago), licensed MIT. It adds 27 tokens to every session and 987 once invoked, about $0.0001 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 commands, from other repositories
ci-debug
Diagnose a failing CI run against an 11-pattern playbook. Classifies the failure, cites the relevant memory entry, proposes the exact fix command — but NEVER applies without explicit user approval. Use when a specific PR check or GitHub Actions run failed and you want a diagnosis instead of speculation. Don't use for…
bug-report
Converts a raw bug report from production into a structured, severity-classified item and routes it to the right next step.
maintain
Run automated maintenance — seeker finds bugs from pod logs and raises GitHub issues, fixer picks them up and creates PRs. Can run as a one-shot or scheduled via /schedule.
debloat
Retroactive whole-repo bloat removal (spec H-2ii). Scores an existing repo on the deterministic bloat axes, writes BLOAT-REPORT.md, and — only behind a passing test-suite safety oracle — proposes gated refactor waves as a PR. The zero-risk adoption hook.
duck-off
Turn off Rubber Duck mode and answer normally.
verify
Run the full verification suite (build, type-check, tests, lint) via a fresh-context verification-runner subagent; reports evidence paths. Read-only by default; opt-in '--fix' runs a bounded auto-fix loop (max 2 cycles). Use before marking featurelist.json status as 'pass'.