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/ttguy0707/codojo/dojo-resetnpx skills add ttguy0707/codojo --skill dojo-resetgit clone --depth 1 https://github.com/ttguy0707/codojoWhat 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 | $0.00402 | $0.01412 |
| Opus 5 | $0.00201 | $0.00706 |
| Sonnet 5 | $0.00080 | $0.00282 |
| Haiku 4.5 | $0.00040 | $0.00141 |
Grade A, and why
dojo-reset 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 3d 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.
What it actually says
dojo-reset — 进度回档工具
一句话定位:展示当前进度,让用户选择回到任意阶段,安全删除后续文件。
何时使用
- ✅ 用户说"重来"、"重新开始"、"从头来"
- ✅ 用户说"回到 S1/S2/S3/S4"
- ✅ 用户说"清除进度"、"重置"、"reset"
- ✅ 用户对当前阶段不满意,想回退重做
前置条件
.codojo/目录存在(否则提示"还没有任何进度,无需重置")
工作流
Step 1:读取状态并展示进度表
读取 .codojo/ 下所有文件,整理并输出:
## 📍 当前学习进度
| 阶段 | 状态 | 产出文件 |
|---|---|---|
| S1 能力评估 | ✅ 已完成 | `open-questions.md` (含 ASSESS_DONE) |
| S2 计划生成 | ✅ 已完成 | `task.md` + `schedule.md` |
| S3 正式教学 | 🔄 进行中 (58%) | `schedule.md` 进度 58% |
| S4 魔改阶段 | ⚪ 未开始 | — |
你想回到哪个阶段?(S1 / S2 / S3 / S4)
Step 2:等待用户选择
用户选择目标阶段后,根据下表确定操作:
| 回档目标 | 保留 | 删除/重置 |
|---|---|---|
| 回到 S1(重头开始) | 无 | 删除 open-questions.md + task.md + schedule.md + plan.md |
| 回到 S2(重新规划) | open-questions.md |
删除 task.md + schedule.md + plan.md |
| 回到 S3(重新学习) | open-questions.md + task.md |
重置 schedule.md 进度为 0% + 删除 plan.md |
| 回到 S4(重新魔改) | open-questions.md + task.md + schedule.md |
删除 plan.md |
Step 3:确认删除
列出将被操作的文件,请求用户确认:
## ⚠️ 回档确认
你选择回到 **S2(重新规划)**,以下文件将被删除:
- ❌ `.codojo/task.md`
- ❌ `.codojo/schedule.md`
- ❌ `.codojo/plan.md`(不存在,跳过)
以下文件保留:
- ✅ `.codojo/open-questions.md`
确认执行?(输入"确认"执行 / "取消"放弃)
Step 4:执行删除/重置
用户确认后:
- 对于"删除"的文件:直接删除
- 对于"重置 schedule.md 进度为 0%":将 schedule.md 中所有 ✅ 替换为 ⚪,总进度行改为 0%
Step 5:完成报告 + 路由
## ✅ 回档完成
已回到 **S2(计划生成)** 阶段。
输入"继续"进入 S2 重新生成学习计划。
回档完成后,用户下一句话会被 dojo-stage 路由器捕获并进入目标阶段。
Gotchas
- 如果
.codojo/不存在,直接提示"还没有任何进度,无需重置",不要创建目录 - 如果用户选择的目标阶段已经是当前阶段(如当前在 S2,用户选"回到 S2"),提示"你已经在 S2,是否要清除 S2 产出重新做?"
- schedule.md 重置时只改进度标记和总进度行,不删除知识点列表本身
- 删除操作不可逆——确认前务必展示完整文件列表
- 如果存在用户自行在
.codojo/下创建的额外文件(非标准产出),不要删除,只操作已知的 4 个标准文件
产出
- 无新文件产出(纯删除/重置操作)
输出风格约束
详见共用 reference:../_shared/output-style-guide.md
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.
- 3d ago First seen · 121 lines · 402 tokens per session scan A a1a2fb6692e7
dojo-reset is a skill published in the GitHub repository ttguy0707/codojo (56 stars, last pushed 2mo ago), licensed MIT. It adds 402 tokens to every session and 1,412 once invoked, about $0.0020 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
openspec-onboard
Guided onboarding for OpenSpec - walk through a complete workflow cycle with narration and real codebase work.
academy-learn
Use when the user wants to be taught an Anthropic product or feature - "teach me Claude Code", "learn Cowork", "academy lesson", "train me on MCP or the Claude API", "quiz me", "next lesson" - or asks for structured learning rather than a one-off answer. Covers Claude Code, Claude.ai, Cowork, Tag, Platform/API, and AI…
offensive-vuln-classes
Exploit development curriculum covering core vulnerability classes with real-world CVE case studies: stack/heap buffer overflows, use-after-free, integer overflows, format strings, type confusion, and race conditions. Use when learning or teaching vuln classes, researching specific CVE patterns, or building exploit…
comet-native
Comet Native 工作流。当用户明确调用 /comet-native、要求启动或恢复 Native change,或入口路由到 Native 时使用。.
comet-classic
Comet Classic 工作流(OpenSpec + Superpowers)。当用户明确调用 /comet-classic、要求启动或恢复 Comet Classic,或 resume-probe 返回可无歧义恢复的 active Classic change 时使用。.
comet
Comet — OpenSpec + Superpowers dual-star development workflow. Start with /comet for automatic phase detection and dispatch to subcommands. Five phases: open → design → build → verify → archive.