context-budget
即時 context 用量導向原生指令，靜態稽核只在明確要求時做
中文翻譯
---
name: context-budget
description: 把即時的 context 檢查導向 Codex 或 Claude Code 原生的計量器，不掃描檔案；只有在被明確要求時，才執行有界限的靜態元件稽核。適用於詢問剩餘容量或已安裝的 context 開銷的 context-budget 需求。
metadata:
origin: ECC
---
# Context Budget
即時的 session 用量，用供應商原生的計量器。把另外一套、
估算性質的安裝稽核，放在明確 opt-in 之後才做。
## Default: Live Context
沒有要求稽核的呼叫，一律當成即時 context 的請求。
包括詢問目前的視窗、剩餘容量、餘裕、token
用量，或 context 明細。
這條預設路徑：
- 不要呼叫或使用工具。
- 不要掃描或讀取檔案。
- 不要執行 shell 指令、供應商 CLI、除錯記錄或 MCP 探索。
- 只回覆原生指令，加上一句簡短的說明。
依目前啟用的 harness 導向：
| Harness | Native command | Guidance |
| --- | --- | --- |
| Codex CLI | `/status` | 顯示目前的 token 用量和剩餘的 context 容量。用 `/statusline` 並啟用 **Context stats** 加 **Token counters**，就能在頁尾常駐顯示計量器。 |
| Codex app | `/status` | 顯示目前對話串的 context 用量和速率限制。 |
| Claude Code | `/context` | 顯示即時的 context 明細。用 `/context all` 看展開的項目。 |
| Other or unknown | None verified | 說明 ECC 無法讀取供應商的即時狀態，並問目前用的是哪個 harness。 |
這些指令記載在 [Codex 指令參考](https://developers.openai.com/codex/cli/slash-commands)和 [Claude Code 指令參考](https://code.claude.com/docs/en/commands)。
Skill 無法代替使用者呼叫 TUI 的斜線指令。絕對不要用估算的掃描
取代原生指令，也絕對不要從「context 很重」或「還剩多少」
這類說法去推斷使用者要求稽核。
## Explicit Static Audit
只有在使用者明確說出
`--audit`、「audit installed components」，或同樣明確無歧義的措辭時，才執行安裝/設定稽核。
`--verbose` 只會改變報告的細節程度，它本身不代表 opt-in 稽核。
如果稽核範圍不明確，在讀取任何東西之前，先問 harness
和安裝根目錄。每次稽核都要有界限而且唯讀：
1. 只檢查指名的 plugin/安裝根目錄，以及指名的 harness 已知的
設定檔。
2. 絕對不要遞迴列舉 workspace 根目錄、家目錄、供應商
快取、對話記錄、除錯記錄或不相關的 worktree。
3. 絕對不要為了計算工具數量而啟動供應商 CLI、MCP 伺服器或除錯 session。
4. 每個元件類別的清單輸出上限是 50 個項目。其餘的用摘要帶過。
5. 不要寫暫存記錄，也不要把設定內容複製進報告。
只稽核跟 eager discovery（預先探索）有關的元件 metadata：
- agent 和 skill 的描述；
- 當 harness 預先探索指令時，指令的描述；
- 在明確指名的範圍內、永遠載入的指示檔案；
- 現有有界限的 manifest 有公開時，已設定的 MCP 工具 schema。
完整的 skill、agent、指令和規則本文，通常是按需載入的內容。
把它們的磁碟大小，跟估算的 eager 開銷分開回報，不要
把每份本文都加進 session 基準裡。
## Audit Output
回傳一份精簡的報告，包含：
- harness 和實際檢查過的路徑；
- 依元件類別估算的 eager/探索開銷；
- 已安裝的數量，和最重的 metadata 項目；
- 假設、無法取得的量測，以及最多三項最佳化建議。
每個計算出來的 token 數字，都是靜態設定開銷的估算，
不是即時的 session context。不要宣稱估算值是供應商回報的、
目前的、精確的，或是已實現節省的證據。把使用者引導回
原生的即時 context 指令，查看目前的用量。
## Optional Selected-Record Diagnostic
只有在使用者為了這個診斷明確選定某個檔案時，才檢查已持久化的記錄。這跟預設的即時 context 請求和安裝稽核是分開的。
做本地檔案診斷時，要明確選定一個穩定、一般的 JSONL 檔案，或是你
打算檢查的快照。把下面範例的路徑換掉；這不會去尋找或重新連回 session。
這段程式碼只會印出彙總的位元組數。它一次讀一行，所以記憶體用量取決於
最大的那筆記錄；避免很大的記錄和還在持續成長的檔案。
```sh
python3 - "/path/to/selected-session.jsonl" <<'EOF'
import json
import sys
total = attachment = other = unclassified = 0
try:
with open(sys.argv[1], "rb") as source:
for raw in source:
size = len(raw)
total += size
try:
record = json.loads(raw.decode("utf-8"))
except (UnicodeDecodeError, json.JSONDecodeError):
unclassified += size
continue
record_type = record.get("type") if isinstance(record, dict) else None
if not isinstance(record_type, str):
unclassified += size
elif record_type == "attachment":
attachment += size
else:
other += size
except OSError:
print("Cannot read selected JSONL file.", file=sys.stderr)
raise SystemExit(1)
pct = attachment * 100.0 / total if total else 0.0
print(f"persisted {total}B | attachment records {attachment}B ({pct:.1f}%) | "
f"other records {other}B | unclassified {unclassified}B")
EOF
```
三個類別加起來等於原始檔案的位元組數，包含換行符號和空白行。
`attachment` 是精確的記錄類型過濾，不保證符合 harness 目前內部的
schema。其他記錄的 `type` 是不同的字串；格式錯誤的 JSON、無效的 UTF-8、非物件的
值、缺少或非字串的 type，以及空白行，都歸為 unclassified。這兩個類別都不代表
「對話」，百分比也只是已持久化位元組數的佔比。
這些數字無法證明目前使用中的 context、剩餘空間、token 用量、計費，或是重新連線時會載入什麼。
要看 harness 回報的目前 context 和用量，請使用對應版本的
[`/context` 和 `/usage` 指令（`/cost` 是別名）](https://code.claude.com/docs/en/commands)。英文原文
---
name: context-budget
description: Routes live context checks to the native Codex or Claude Code meter without scanning files, and performs a bounded static component audit only when explicitly requested. Use for context-budget requests about remaining capacity or installed context overhead.
metadata:
origin: ECC
---
# Context Budget
Use the provider's native meter for live session usage. Keep the separate,
estimated installation audit behind an explicit opt-in.
## Default: Live Context
Treat an invocation with no audit request as a live-context request. This
includes requests for the current window, remaining capacity, headroom, token
usage, or a context breakdown.
For this default path:
- Do not call or use tools.
- Do not scan or read files.
- Do not run shell commands, provider CLIs, debug logging, or MCP discovery.
- Reply with only the native command and one short explanation.
Route by the active harness:
| Harness | Native command | Guidance |
| --- | --- | --- |
| Codex CLI | `/status` | Shows current token usage and remaining context capacity. Use `/statusline` and enable **Context stats** plus **Token counters** for a persistent footer meter. |
| Codex app | `/status` | Shows current thread context usage and rate limits. |
| Claude Code | `/context` | Shows the live context breakdown. Use `/context all` for expanded items. |
| Other or unknown | None verified | State that ECC cannot read live provider state and ask which harness is active. |
These commands are documented in the [Codex command reference](https://developers.openai.com/codex/cli/slash-commands) and [Claude Code command reference](https://code.claude.com/docs/en/commands).
A skill cannot invoke a TUI slash command on the user's behalf. Never replace
the native command with an estimated scan and never infer an audit request from
phrases such as “context is heavy” or “how much is left.”
## Explicit Static Audit
Run an installation/configuration audit only when the user explicitly says
`--audit`, “audit installed components,” or equivalent unambiguous wording.
`--verbose` changes report detail; it does not opt into an audit by itself.
If the audit scope is ambiguous, ask for the harness and installation root
before reading anything. Keep every audit bounded and read-only:
1. Inspect only the named plugin/install root and the named harness's known
configuration files.
2. Never recursively enumerate the workspace root, home directory, provider
cache, transcripts, debug logs, or unrelated worktrees.
3. Never launch a provider CLI, MCP server, or debug session to count tools.
4. Cap inventory output at 50 entries per component class. Summarize the rest.
5. Do not write temporary logs or copy configuration content into the report.
Audit only the component metadata relevant to eager discovery:
- agent and skill descriptions;
- command descriptions when the harness discovers them eagerly;
- always-loaded instruction files in the explicitly named scope;
- configured MCP tool schemas when an existing bounded manifest exposes them.
Full skill, agent, command, and rule bodies are generally on-demand content.
Report their disk size separately from estimated eager overhead instead of
adding every body to the session baseline.
## Audit Output
Return a compact report containing:
- harness and exact paths inspected;
- estimated eager/discovery overhead by component class;
- installed counts and the heaviest metadata entries;
- assumptions, unavailable measurements, and up to three optimizations.
Every calculated token number is an estimate of static configuration overhead,
not live session context. Do not claim that an estimate is provider-reported,
current, exact, or evidence of realized savings. Direct the user back to the
native live-context command for current usage.
## Optional Selected-Record Diagnostic
Inspect a persisted record only when the user explicitly selects that file for this diagnostic. This is separate from the default live-context request and the installation audit.
For a local file diagnostic, explicitly select a stable, regular JSONL file or a snapshot you
intend to inspect. Replace the example path below; this does not find or reconnect a session.
The snippet prints aggregate byte counts only. It reads one line at a time, so memory use depends
on the largest record; avoid very large records and actively growing files.
```sh
python3 - "/path/to/selected-session.jsonl" <<'EOF'
import json
import sys
total = attachment = other = unclassified = 0
try:
with open(sys.argv[1], "rb") as source:
for raw in source:
size = len(raw)
total += size
try:
record = json.loads(raw.decode("utf-8"))
except (UnicodeDecodeError, json.JSONDecodeError):
unclassified += size
continue
record_type = record.get("type") if isinstance(record, dict) else None
if not isinstance(record_type, str):
unclassified += size
elif record_type == "attachment":
attachment += size
else:
other += size
except OSError:
print("Cannot read selected JSONL file.", file=sys.stderr)
raise SystemExit(1)
pct = attachment * 100.0 / total if total else 0.0
print(f"persisted {total}B | attachment records {attachment}B ({pct:.1f}%) | "
f"other records {other}B | unclassified {unclassified}B")
EOF
```
The three categories add up to the original file bytes, including line endings and blank lines.
`attachment` is an exact record-type filter, not a guarantee about a harness's current internal
schema. Other records have a different string `type`; malformed JSON, invalid UTF-8, nonobject
values, missing or non-string types, and blank lines are unclassified. Neither category means
"conversation," and the percentage is only a share of persisted bytes.
These counts do not establish active context, remaining room, token usage, billing, or what a
reconnect loads. For current harness-reported context and usage, use the version-appropriate
[`/context` and `/usage` commands (`/cost` is an alias)](https://code.claude.com/docs/en/commands).