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/luohaothu/everything-codex/evalgit clone --depth 1 https://github.com/Luohaothu/everything-codexWhat 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 | $0.00665 |
| Opus 5 | $0.00000 | $0.00332 |
| Sonnet 5 | $0.00000 | $0.00133 |
| Haiku 4.5 | $0.00000 | $0.00067 |
Grade A, and why
eval 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 yesterday.
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.
What it actually says
Eval 命令
管理基于评估的开发工作流。
用法
/eval [define|check|report|list] [feature-name]
定义评估
/eval define feature-name
创建新的评估定义：
- 使用模板创建
.claude/evals/feature-name.md：
## EVAL: 功能名称
创建于: $(date)
### 能力评估
- [ ] [能力 1 的描述]
- [ ] [能力 2 的描述]
### 回归评估
- [ ] [现有行为 1 仍然有效]
- [ ] [现有行为 2 仍然有效]
### 成功标准
- 能力评估的 pass@3 > 90%
- 回归评估的 pass^3 = 100%
- 提示用户填写具体标准
检查评估
/eval check feature-name
为功能运行评估：
- 从
.claude/evals/feature-name.md读取评估定义 - 对于每个能力评估：
- 尝试验证标准
- 记录 通过/失败
- 在
.claude/evals/feature-name.log中记录尝试
- 对于每个回归评估：
- 运行相关测试
- 与基线比较
- 记录 通过/失败
- 报告当前状态：
EVAL CHECK: feature-name
========================
Capability: X/Y passing
Regression: X/Y passing
Status: IN PROGRESS / READY
报告评估
/eval report feature-name
生成全面的评估报告：
EVAL REPORT: feature-name
=========================
Generated: $(date)
CAPABILITY EVALS
----------------
[eval-1]: PASS (pass@1)
[eval-2]: PASS (pass@2) - required retry
[eval-3]: FAIL - see notes
REGRESSION EVALS
----------------
[test-1]: PASS
[test-2]: PASS
[test-3]: PASS
METRICS
-------
Capability pass@1: 67%
Capability pass@3: 100%
Regression pass^3: 100%
NOTES
-----
[Any issues, edge cases, or observations]
RECOMMENDATION
--------------
[SHIP / NEEDS WORK / BLOCKED]
列出评估
/eval list
显示所有评估定义：
EVAL DEFINITIONS
================
feature-auth [3/5 passing] IN PROGRESS
feature-search [5/5 passing] READY
feature-export [0/4 passing] NOT STARTED
参数
$ARGUMENTS:
define <name>- 创建新的评估定义check <name>- 运行并检查评估report <name>- 生成完整报告list- 显示所有评估clean- 删除旧的评估日志（保留最近 10 次运行）
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.
- yesterday First seen · 123 lines · 0 tokens per session scan A dbf1b393e1b0
eval is a command published in the GitHub repository Luohaothu/everything-codex (24 stars, last pushed 21d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 665 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 2026-08-30.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.