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/madappgang/claude-code/revertnpx skills add MadAppGang/claude-code --skill revertgit clone --depth 1 https://github.com/MadAppGang/claude-codeWrote 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/madappgang/claude-code/revert)<a href="https://agentmods.dev/skills/madappgang/claude-code/revert"><img src="https://agentmods.dev/badge/skills/madappgang/claude-code/revert.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 | $0.00018 | $0.01800 |
| Opus 5 | $0.00009 | $0.00900 |
| Sonnet 5 | $0.00004 | $0.00360 |
| Haiku 4.5 | $0.00002 | $0.00180 |
Grade A, and why
revert 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 4d 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 — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
plugin: conductor updated: 2026-01-20
**Before starting**, create todo list with these 5 phases:
1. Scope Selection - Identify what to revert (track/phase/task)
2. Impact Analysis - Find commits, files, status changes
3. User Confirmation - Present impact and get approval
4. Execution - Create revert commits and update files
5. Validation - Verify consistency and report results
**Update continuously**:
- Mark "in_progress" when starting each phase
- Mark "completed" immediately after finishing
- Keep only ONE phase "in_progress" at a time
</todowrite_requirement>
<confirmation_required>
ALWAYS require explicit user confirmation before:
- Reverting any commits
- Modifying plan.md status
- Deleting track files
Show exactly what will be changed BEFORE doing it.
</confirmation_required>
<non_destructive_default>
Default to creating revert commits, not force-pushing.
Preserve git history unless user explicitly requests otherwise.
</non_destructive_default>
<state_validation>
After any revert:
1. Verify plan.md matches git state
2. Verify metadata.json is consistent
3. Run project quality checks
4. Report any inconsistencies
</state_validation>
</critical_constraints>
<core_principles> Revert by logical units (track/phase/task), not raw commits. A task might have multiple commits - revert them together.
<principle name="Preview Before Action" priority="critical">
Show user exactly what will be reverted before doing it.
List commits, files, status changes.
</principle>
<principle name="Graceful Degradation" priority="high">
If full revert fails, offer partial revert options.
Never leave project in inconsistent state.
</principle>
</core_principles>
<phase number="2" name="Impact Analysis">
<step>Read metadata.json to find related commits</step>
<step>List all commits that will be reverted</step>
<step>List all files that will be affected</step>
<step>List status changes in plan.md</step>
</phase>
<phase number="3" name="User Confirmation">
<step>Present impact analysis to user</step>
<step>Ask for explicit confirmation</step>
<step>If declined, abort with no changes</step>
</phase>
<phase number="4" name="Execution">
<step>Create revert commits for each original commit</step>
<step>Update plan.md statuses back to [ ]</step>
<step>Update metadata.json to reflect revert</step>
<step>Remove completed tasks from history</step>
</phase>
<phase number="5" name="Validation">
<step>Verify git state matches plan.md</step>
<step>Run project quality checks</step>
<step>Report final state to user</step>
</phase>
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.
- 4d ago First seen · 239 lines · 18 tokens per session scan A 8c5fdf91dcdc
revert is a skill published in the GitHub repository MadAppGang/claude-code (279 stars, last pushed 5mo ago), licensed MIT. It adds 18 tokens to every session and 1,800 once invoked, about $0.0001 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
run-task
Execute a single Todo task through In Progress to Review, meeting every acceptance criterion with tests and vibe-lint checks. Refuses Planning-status tasks. Invoked as /agiflow:run-task . Uses gettask, updatetask, createtaskcomment.
state-trees
Create, inspect, and edit StateTree assets — states, tasks, transitions, conditions, considerations, and property bindings for AI behavior and game logic (StateTreeService). Use when the user asks to build a StateTree, add states/tasks/transitions, bind task properties, set up Utility AI considerations, or wire…
task-loop
任务目标驱动执行闭环预装 skill,整合任务识别/规划/派发搜推/验收/BBS 接力/arch 场景规划变体(planning-arch)与架构师名册 mock(arch-analysis)共七段为单一 skill,预装到所有 bot 等同各段单独安装到对应 bot;各段按各自触发词自门控仅命中段执行(用户面 /task 或 [RESUMETASK] 或副屏标签命中识别;框架 [planning] 命中规划,arch 场景含「某某某公司」命中 planning-arch 变体;框架 [search] 命中派发搜推;worker 叶子自验收命中验收;引擎 BBS 通知命中接力,其 scoped 叶子 instruction…
bbs-relay-pickup
被唤醒时从 task API 发现 BBS 升级任务、CAS 占根、自判剩余、挂节点、执行、经回投写回.
task-planning-arch
计算任务 gap 并产出下一步可执行子任务 List[TaskSpec];gap 已闭返回空数组。对齐 arch 场景(架构师名册/技术栈概览/双视角分析)确定式分解——按根目标交付物集合 + donechildren 查表(参照 task-planning storage 特例,非自由 LLM 分解)。.
task-search
在框架预查的候选 bot 集里决出执行者(who)与协作方式(how),返回 4 态 SearchResult(HITSINGLE/HITGROUP/HITMULTIBOTS/MISS)。对齐案例剧本确定式映射。.