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 skills/kairyou/agent-tools/at-self-evalnpx skills add kairyou/agent-tools --skill at-self-evalgit clone --depth 1 https://github.com/kairyou/agent-toolsWrote 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/skills/kairyou/agent-tools/at-self-eval)<a href="https://agentmods.dev/skills/kairyou/agent-tools/at-self-eval"><img src="https://agentmods.dev/badge/skills/kairyou/agent-tools/at-self-eval.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 | $0.00041 | $0.01465 |
| Opus 5 | $0.00020 | $0.00732 |
| Sonnet 5 | $0.00008 | $0.00293 |
| Haiku 4.5 | $0.00004 | $0.00146 |
Grade A, and why
at-self-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 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Self-Evaluation Summary
resolve evidence -> group by business line -> deduplicate -> <=8 outcomes -> review
Author and date window
Normalize flags or plain language such as 统计1-3月的产出 and 统计上半年的工作
into (author, from, to). Explicit input wins; fill only missing values:
| User gave | Resolve to |
|---|---|
from and to |
use both |
only from |
to = today |
only to |
from = Jan 1 of that year |
| no range | current quarter |
Parse half-years, calendar quarters, month ranges, and rolling periods. A spoken
period without a year means the current year, except months still ahead of today,
which mean the previous year. Query through <to + 1 day> because Git's --until is exclusive.
Always exclude merge commits.
Use an explicit author when supplied; otherwise resolve it independently per repository
with git -C <root> config user.name. Never infer aliases or use the remote login as
the author. List candidates with git -C <root> log --no-merges --since=<from> --until=<to+1day> --format=%H%x09%an --branches HEAD <upstream refs>, taking the
upstream refs from git -C <root> for-each-ref --format=%(upstream) refs/heads/;
passing no ref walks only the current branch, so work on an unmerged branch reads as
no activity, while --all reaches into remote branches nobody tracks. Keep the rows
whose %an equals that name exactly. Never pass --author: it matches the whole
Name <email> header, so anchored patterns silently match nothing. If no commits
match, report that together with the author names the window actually holds; do not
try spelling or language variants. When results exist, mention once that the
user can provide other author names if needed.
Project evidence
Read optional workProjects from ~/.agent-tools/config.jsonc. An entry is a path
or { "path", "prompt" }, where the prompt is free text this skill follows for that
project, such as how to label items or which commits to skip.
- No project named: current Git repository plus configured projects.
- Projects named directly: only those projects.
- "Also include" /
另外包含: add them to the default scope.
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 · 124 lines · 41 tokens per session scan A 30da1c56f181
at-self-eval is a skill published in the GitHub repository kairyou/agent-tools (177 stars, last pushed 5d ago), licensed MIT. It adds 41 tokens to every session and 1,465 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
minimal-code-discipline
YAGNI-ladder coding discipline for writing changes — existence-first, reuse before writing, dependency ladder, shortest correct diff, with non-negotiables that must never be minimized away.
workflow
Use when a task is too large for turn-by-turn orchestration and should run through the big-task workflow lane: system-wide changes, large migrations, repo-wide audits, high-confidence verification, or tasks explicitly asking to run a workflow. Claude Code uses native dynamic workflows; Codex, OpenCode, and Grok use…
give-me-tips
Explains any senpi tip in depth, including Tip: lines in the TUI. Use when the user asks about a tip, what a tipped feature does, or which tips they can see.
cmux-keyboard-shortcuts
Guide and apply cmux keyboard shortcut customization. Use when the user asks to customize, rebind, unbind, reset, audit, or create shortcut templates for cmux, including tmux-style, Vim-style, terminal-first, browser-heavy, iTerm/Terminal-like, or agent-triage layouts.
cmux-custom-sidebar
Build a custom cmux sidebar from a plain-language request. Use when the user asks for a custom sidebar, a sidebar that shows their workspaces/tabs/PRs/clock, a vibe-coded sidebar, or anything involving files in /.config/cmux/sidebars/. Covers authoring the interpreted SwiftUI-style file, enabling the beta flag…
cmux-customization
Customize cmux for an end user. Use when changing cmux.json actions, custom commands, workspace layouts, plus-button behavior, surface tab bar buttons, Command Palette entries, Dock controls, sidebar and app settings, shortcuts, notifications, browser routing, examples-library presets, or Ghostty-backed terminal…