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/ryanzhao1011/workframe/rollbacknpx skills add ryanzhao1011/workframe --skill rollbackgit clone --depth 1 https://github.com/ryanzhao1011/workframeWhat 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 | $0.00032 | $0.01097 |
| Opus 5 | $0.00016 | $0.00549 |
| Sonnet 5 | $0.00006 | $0.00219 |
| Haiku 4.5 | $0.00003 | $0.00110 |
Grade A, and why
rollback 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 2d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/core:rollback 回滚自动变更
用途
用户显式 /core:rollback 时执行。Claude 不会自动调用。
回滚目标：
- L1 Librarian 变更：从
logs/librarian-snapshots/{YYYY-MM-DD}/{HH-mm-ss}-<role>-MEMORY.md还原 MEMORY.md，同时从同目录的{HH-mm-ss}-<role>-memory-index-entries.json还原对应 sidecar entries（避免 MEMORY.md 与.claude/workframe-state/memory-index.json不一致） - L2 self-iteration 变更：从
{target-dir}/versions/{YYYYMMDD-HHmmss}-{target-basename}.bak还原；若 rollback-index entry 的targets是数组（多文件 L2 变更），逐一回滚每个 target 的备份文件 - 指定 proposal：按 rollback-index entry 中的
targets[]还原（这是当时实际执行的候选的 targets，不含未执行候选的 target——见self-iteration/SKILL.md阶段 5 step 7 约束）；若 entry 缺失，降级到读projects/proposals/applied/PROP-<id>.yaml的proposed_change.targets[]（注意旧版可能多 candidate，需与applied_option字段交叉确认）
输入
- 无参数 → 列出最近可回滚的 10 项，
AskUserQuestion让用户选 PROP-20260424-001→ 直接回滚该提案last→ 回滚最近一次
执行步骤
- Read
.claude/workframe-state/rollback-index.json（由 self-iteration 阶段 5 写入 entry），列出候选- v2 格式（多文件 L2 变更）：
{"id":"RB-<YYYYMMDD-NNN>","proposal_id":"<id>","targets":["<path1>","<path2>"],"backups":["<path1>","<path2>"],"applied_at":"<ISO-8601>","applied_option":"<A|B|C>"} - legacy 格式（v1 单 target，仍需兼容历史 entry）：
{"id":...,"proposal_id":...,"target":"<path>","backup":"<path>","applied_at":...,"applied_option":...} - 解析规则：优先读
targets/backups数组；若不存在则回退到target/backup单字符串字段并视为单元素列表
- v2 格式（多文件 L2 变更）：
- 若候选为空，降级扫描：
logs/librarian-snapshots/**/*-MEMORY.md最近 10 个projects/proposals/applied/*.yaml最近 10 个（反查其applied_option对应的 target +{target-dir}/versions/{YYYYMMDD-HHmmss}-{target-basename}.bak备份）
- 用
AskUserQuestion让用户选一项 - 执行回滚：
- 读备份文件 → Write 到目标文件（多 target 时逐一执行）
- L1 MEMORY 类回滚：同步还原 sidecar entries（读取与快照同目录的
{HH-mm-ss}-<role>-memory-index-entries.json，把其中条目合并回.claude/workframe-state/memory-index.json的entries字典，覆盖同 key） - 若是 proposal，将其从
applied/移回rejected/并记录回滚原因
- 追加 events.jsonl（多 target 时逐一 append）：
{"ts":"<now ISO-8601>","type":"rollback_applied","target":"<path>","source":"<backup>"} - 追加
projects/changelog.md一条## <date> Rollback记录 - 提示用户已回滚 + 让其手动 verify 目标文件
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.
- 2d ago First seen · 55 lines · 32 tokens per session scan A 31d7e75383f0
rollback is a skill published in the GitHub repository ryanzhao1011/workframe (4 stars, last pushed 15d ago), licensed MIT. It adds 32 tokens to every session and 1,097 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 2026-08-31.
Other skills, from other repositories
check-understanding
Phase quiz for AI Engineering from Scratch. Trigger with "quiz me", "test phase", "check my understanding", "do I know phase 3", or /check-understanding .
find-your-level
Interactive quiz that maps your AI/ML knowledge to a starting point in the 260-lesson, 20-phase AI Engineering from Scratch curriculum. Trigger phrases: "where should I start", "find my level", "what do I know", "which phase", "assess my knowledge", "placement test", "skip ahead".
agent-memory-mcp
A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
eval-agents
Audit Claude Code agents defined in .claude/agents/ for description specificity, model tier appropriateness, tools scoping, and system prompt quality. Detects dispatch ambiguity between agents, flags over-permissive tool grants, and checks for human-in-the-loop patterns that break programmatic orchestration. Use when…
check-cache-bugs
Audit Claude Code setup for cache bugs (CC#40524): sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5.
git-ai-archaeology
Analyze AI config evolution in a git repo. Use when mapping AI adoption history, finding when configs were first introduced, charting commit velocity by month, or identifying maturity phases in a project's AI tooling.