Agile Product Owner
davila7/claude-code-templates
Agile product ownership toolkit for Senior Product Owner including INVEST-compliant user story generation, sprint planning, backlog management, and velocity tracking.
返工预防工程 Owner — 当任务涉及返工率、一次通过率、反复返修、复审持续出现新问题、重复逃逸、whyMissed 复发、预防措施有效性或希望把问题发现前移时使用；要求区分返工与需求变化，建立可比较基线，并用后续任务的前瞻证据验证控制是否有效。
AGPL-3.0Auto-check passed
Install Rework Prevention Engineering
$ npx skills add devcodex-labs/devcodex --skill rework-prevention-engineering -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install devcodex-labs/devcodex rework-prevention-engineering --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/devcodex-labs/devcodex.git skills-src && mkdir -p .claude/skills && cp -r skills-src/content/skills/rework-prevention-engineering .claude/skills/rework-prevention-engineering && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "rework-prevention-engineering" agent skill from https://github.com/devcodex-labs/devcodex/tree/main/content/skills/rework-prevention-engineering into .claude/skills/rework-prevention-engineering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rework-prevention-engineering", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/devcodex-labs/devcodex/tree/main/content/skills/rework-prevention-engineeringType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add devcodex-labs/devcodex --skill rework-prevention-engineering -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install devcodex-labs/devcodex rework-prevention-engineering --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/devcodex-labs/devcodex.git skills-src && mkdir -p .agents/skills && cp -r skills-src/content/skills/rework-prevention-engineering .agents/skills/rework-prevention-engineering && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "rework-prevention-engineering" agent skill from https://github.com/devcodex-labs/devcodex/tree/main/content/skills/rework-prevention-engineering into .agents/skills/rework-prevention-engineering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rework-prevention-engineering", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add devcodex-labs/devcodex --skill rework-prevention-engineering -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install devcodex-labs/devcodex rework-prevention-engineering --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/devcodex-labs/devcodex.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/content/skills/rework-prevention-engineering .cursor/skills/rework-prevention-engineering && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "rework-prevention-engineering" agent skill from https://github.com/devcodex-labs/devcodex/tree/main/content/skills/rework-prevention-engineering into .cursor/skills/rework-prevention-engineering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rework-prevention-engineering", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/devcodex-labs/devcodex.git --path content/skills/rework-prevention-engineering--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add devcodex-labs/devcodex --skill rework-prevention-engineering -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install devcodex-labs/devcodex rework-prevention-engineering --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/devcodex-labs/devcodex.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/content/skills/rework-prevention-engineering .gemini/skills/rework-prevention-engineering && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "rework-prevention-engineering" agent skill from https://github.com/devcodex-labs/devcodex/tree/main/content/skills/rework-prevention-engineering into .gemini/skills/rework-prevention-engineering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rework-prevention-engineering", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install devcodex-labs/devcodex rework-prevention-engineeringInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add devcodex-labs/devcodex --skill rework-prevention-engineering -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/devcodex-labs/devcodex.git skills-src && mkdir -p .github/skills && cp -r skills-src/content/skills/rework-prevention-engineering .github/skills/rework-prevention-engineering && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "rework-prevention-engineering" agent skill from https://github.com/devcodex-labs/devcodex/tree/main/content/skills/rework-prevention-engineering into .github/skills/rework-prevention-engineering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rework-prevention-engineering", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add devcodex-labs/devcodex --skill rework-prevention-engineering -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install devcodex-labs/devcodex rework-prevention-engineering --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/devcodex-labs/devcodex.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/content/skills/rework-prevention-engineering .opencode/skills/rework-prevention-engineering && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "rework-prevention-engineering" agent skill from https://github.com/devcodex-labs/devcodex/tree/main/content/skills/rework-prevention-engineering into .opencode/skills/rework-prevention-engineering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rework-prevention-engineering", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
rework-prevention-engineering- GitHub stars
- 439
- Token cost
- ~1.6k tokens
- SKILL.md length
- 407 words
- Files
- 3
- Skills in repo
- 70
- Repo updated
- First seen
- Licence
- AGPL-3.0
At a glance
返工预防工程 Owner — 当任务涉及返工率、一次通过率、反复返修、复审持续出现新问题、重复逃逸、whyMissed 复发、预防措施有效性或希望把问题发现前移时使用；要求区分返工与需求变化，建立可比较基线，并用后续任务的前瞻证据验证控制是否有效。
- Works in 7 steps: 建立 baselineWindow 和可比较 WorkUnit 边界。 → 分类事件并完成双根因。 → 选择目标前移阶段和最小有效控制。 → …
- SKILL.md covers 职责, ReworkPreventionGate, 度量合同 and ReworkRiskProfile, plus 5 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Rework Prevention Engineering is an agent skill from devcodex-labs/devcodex. 返工预防工程 Owner — 当任务涉及返工率、一次通过率、反复返修、复审持续出现新问题、重复逃逸、whyMissed 复发、预防措施有效性或希望把问题发现前移时使用；要求区分返工与需求变化，建立可比较基线，并用后续任务的前瞻证据验证控制是否有效。
Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files (for example `agents/openai.yaml` and `repair-prevention-assessment.schema.json`).
The repository describes itself as: Intent-driven AI coding workflow runtime for consistent context, skills, approvals, validation, and handoffs across six AI coding hosts. The licence is AGPL-3.0.
Example prompts
- “/rework-prevention-engineering”
Workflow steps
7 steps, taken from the first numbered list in SKILL.md.
- 建立 baselineWindow 和可比较 WorkUnit 边界。
- 分类事件并完成双根因。
- 选择目标前移阶段和最小有效控制。
- 将控制注册到明确 owner/consumer/probe。
- 在后续可比较任务中收集 prospective evidence。
- 同时记录命中、漏拦、误报、额外成本和晚发现阶段变化。
- 达标则建议 gray→active；无改善、误报高或成本过大则调整、回滚或退役。
What it can do on your machine
Read from SKILL.md and the folder at commit 1dd4525. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Rework Prevention Engineering loads about 1.6k tokens when it runs. Until then it costs about 39 tokens; SKILL.md has 407 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from devcodex-labs/devcodex at commit 1dd4525, republished under its AGPL-3.0 licence (© devcodex-labs). 407 words, ~1,563 tokens.
Download SKILL.mdSave it as
.claude/skills/rework-prevention-engineering/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- rework-prevention-engineering
- description
- 返工预防工程 Owner — 当任务涉及返工率、一次通过率、反复返修、复审持续出现新问题、重复逃逸、whyMissed 复发、预防措施有效性或希望把问题发现前移时使用；要求区分返工与需求变化，建立可比较基线，并用后续任务的前瞻证据验证控制是否有效。
Rework Prevention Engineering
职责
把“复审后继续修问题”升级为可定义、可前移、可度量、可回滚的返工预防工程。不得用增加复审轮数、隐藏 finding、延迟完成声明或把返工改名为计划迭代制造指标改善。
ReworkPreventionGate
WorkUnit 与事件分类
先冻结 WorkUnit：必须锚定已确认需求/问题、ExecutionContract batch、目标门禁和可比较任务类型。只有同时满足以下条件才记录 ReworkEvent：
- 问题属于原确认范围和当时可获得的项目事实；
- 对应工作已通过目标阶段或被宣称完成；
- 为解决问题需要重新分析、设计、修改、验证或交付。
事件分类必须为：rework / scope-change / external-change / planned-iteration / same-phase-catch。后四类不得计入返工率，但要保留分类依据，禁止用重命名规避真实返工。
双根因
每个 ReworkEvent 同时记录：
| 字段 | 要求 |
|---|---|
defectRootCause | 缺陷、遗漏或错误判断本身为什么发生 |
controlFailure | 哪个需求、方案、实现、测试、复审或发布控制应拦截却没有拦截 |
escapedFrom / detectedAt | 应发现阶段与真实发现阶段 |
whyMissed | 范围、消费者、证据、探针、时序、权威源或执行偏差 |
clusterId | 已知模式簇；新模式可先标 candidate |
前移控制
选择能在更早阶段阻断且总成本最低的控制层：prompt / contract / checklist / static probe / unit fixture / integration replay / hook / tool。已有规则仍复发时，单纯再加说明文字不是有效 prevention；必须评估能否物化为可执行消费者或确定性探针。
方案审查存在多个相互独立的潜在 blocker 时，优先采用 BlockerAggregationGate：同阶段继续安全独立检查、冻结完整 BlockerSnapshot、统一修正并全阶段重跑。首个红项即停止会把同批问题推迟到下一轮，属于返工放大控制；仅 invalid-premise / destructive-side-effect / evidence-contamination 可 fail-fast。
度量合同
FirstPassYield = 无 ReworkEvent 即 accepted 的可比较 WorkUnit / 全部可比较完成 WorkUnitWorkUnitReworkRate = 至少一个 ReworkEvent 的 WorkUnit / 全部可比较完成 WorkUnitReworkEventDensity = ReworkEvent / WorkUnitRepeatEscapeRate = 已知 cluster 复发事件 / 全部 ReworkEventPreventionHitRate = 在目标阶段前被控制拦截的已知风险机会 / 全部已知风险机会LateDiscoveryCost：记录 requirement→plan→implementation→ECR→release→post-release 发现阶段；工时、Token、文件数只作可选成本证据。
指标必须按任务类型、复杂度和严重度分层；样本不足时输出 insufficient-sample，不得跨不可比较任务排名。
ReworkRiskProfile
普通低风险任务使用轻量卡：riskCluster / targetPhase / preventionControl / evidence / result。以下任一条件升级完整模式：P0/P1、安全、控制面、公共契约、发布、多批次、角色交接、同簇累计 ≥3 个 finding/返修/逃逸，或历史 WorkUnitReworkRate 高于当前项目阈值。
完整模式必须产出：ReworkEventLedger、EscapePatternCluster、PreventionControlSet、EffectivenessScorecard 和 rollback/sunset 条件。
与 active RepairPreventionAssessmentGate 的关系
所有 repair task 在 accepted 前先执行 active repair-prevention-assessment 的 RepairPreventionAssessmentGate。机器结构以 active Owner 的 repair-prevention-assessment.schema.json 为准，确定性判定仍由 scripts/lib/repair-prevention-assessment.js 承担。本 gray Skill 只消费 assessment 结果来建立返工簇和前瞻效果试验；不得成为 active workflow 的 mandatory dependency。本目录的同名 schema 仅作既有包路径兼容镜像，必须与 canonical schema 字节一致。
本 Gate 同时给出两个互不替代的结论：
immediateClosureEvidence只证明当前问题已修复，可允许当前 repair 关闭；prospectiveEvidencePlan只证明长期控制的试验/效果状态。当前事件重跑通过一律是retrospective-only，不得把 provisional control 晋级为 active/effective。
决策与升级摘要
以下为 gray 效果工程消费 assessment 时需要的生命周期摘要；字段真相与阻断语义以 active Owner 为准。
preventionDecision | 使用条件 | 生命周期 |
|---|---|---|
existing-control-restored | 已有有效控制因执行/接线偏差未生效，本次恢复其消费者或执行链 | 保持既有 active；不得用当前重跑重新证明效果 |
new-control-provisional | 新增或实质改变 prompt/contract/checklist/probe/test/hook/tool 控制 | draft/gray；达到前瞻样本门槛后才可申请 active |
no-new-control | 已有控制已足够、一次性不可泛化、成本高于风险或不存在更早发现点 | 必须选择标准 reason 并给独立证据；不能用“已修复”作理由 |
emergency-active | P0/安全/控制面高危问题需要先启用控制 | active-expiring；必须有明确授权、前瞻补证、回滚触发和 reviewAt |
低/普通风险首次 repair 可用 mode=light，但 schema 的双根因、回归 seed、负向 case、当前关闭证据和 rollback/sunset 仍不可缺。P0/P1、安全、控制面、公共契约、发布、多批次、角色交接、high/critical 或 repeat escape 必须 mode=full，追加 whyMissed / authorizationEvidence / independentReReviewPlan。
重复逃逸不得选择 no-new-control 或只恢复原说明文案；必须升级 new-control-provisional，紧急场景才允许 emergency-active。全模式下 regression seeds、negative cases、Owner、consumers 和 rollback/sunset 任何一项缺失，都不得把 repair collaboration contract 转为 accepted。
Show full SKILL.md (181 more words)Show less
ReworkEffectivenessLoop
- 建立 baselineWindow 和可比较 WorkUnit 边界。
- 分类事件并完成双根因。
- 选择目标前移阶段和最小有效控制。
- 将控制注册到明确 owner/consumer/probe。
- 在后续可比较任务中收集 prospective evidence。
- 同时记录命中、漏拦、误报、额外成本和晚发现阶段变化。
- 达标则建议 gray→active；无改善、误报高或成本过大则调整、回滚或退役。
同一个事件的“修复后重跑通过”只能证明本事件关闭，不能证明 prevention 有效。普通候选至少需要 3 个可比较 WorkUnit 或 2 个独立任务/项目上下文的前瞻证据；P0 安全/控制面可先紧急启用，但必须补后验效果复证。
发布候选因普通 working diff 未覆盖 untracked 文件而逃逸时，将 CandidateDiffCompletenessGate 作为 gray prevention：defectRootCause 记录文件缺陷，controlFailure 记录候选证据范围错误，escapedFrom 与 detectedAt 分离；当前事件的 staged rerun 仅关闭本事件，后续可比较发布 WorkUnit 才能形成 prospective effectiveness evidence。
Turn Liveness Prevention Trial
long-task-silent-orphaned-turn 簇以 OrphanInProgressCount / MeanStaleDetectionTime / RecoverySuccessRate / FalseStallRate / DuplicateMutationRate / UserWaitWithoutFeedback 为效果指标。控制层由 ai-agent-system-architecture 的 TurnLivenessRecoveryGate、Hook replay 和可选 gray sidecar 组成；当前停滞案例修复通过只关闭本 WorkUnit，不能证明防复发有效。
sidecar 晋级至少需要 5 个可比较长任务 WorkUnit，包含 2 个真实长工具和 2 个故障注入样例，并记录误报、额外状态 I/O 和恢复成本。误报超过项目预算、重复 mutation 非零或宿主边界不清时，回退为提示-only/one-shot，保留 checkpoint 和 terminal invariant。
生命周期与授权
新控制按 draft → gray → active 管理，复用 skill-lifecycle-governance；规范候选与自动化复用 evolution-governance 的 candidate-only 授权。返工率目标不得授权 AI 自动修改 active 规范、源码、数据或发布面。
与其他 Skill 的关系
review-checklist/audit-common：提供 coverage 与 escape evidence。quality-strategy/test-router：选择风险驱动验证组合。evolution-governance：管理候选、gray 试点、升级、回滚和授权。spec-absorption：执行 ReworkReductionValueGate 与消费者证明。brand-visual-quality：提供品牌资产 WorkUnit、VisualBlockerResetRecord、复发和人工修正数据；当前资产修复通过只关闭该 WorkUnit，仍需后续可比较样本才能证明返工预防有效。ai-agent-system-architecture/host-contract-verification：提供 Turn Liveness 状态、能力边界和 direct replay；返工 Skill 只拥有前瞻效果评估，不复制运行时状态机。report：输出 baseline、事件分类、效果和剩余风险。execution-contract/fix-default/fix-security：所有 repair 的 accepted 前入口；只引用 activerepair-prevention-assessmentOwner 的 assessment result，本 gray Gate 不拥有完成判定。review-checklist/test-router：分别核对 assessment 完整性和 immediate/prospective 两条证据路线，不重定义生命周期阈值。
反模式
- 把用户新增需求、外部变化或同阶段主动发现计为返工。
- 用复审次数或最终零 finding 单独证明返工下降。
- 用当前事件修复后的通过结果冒充前瞻效果。
- 为降低指标而减少审查、隐藏 finding、延迟 accepted 或扩大 planned-iteration。
- 已有规则复发时继续堆 instructions 文案，却不补执行消费者或探针。
- 把
no-new-control当作免填项，或用当前修复测试通过证明长期 prevention 已有效。
© devcodex-labs, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 2 other files in content/skills/rework-prevention-engineering of devcodex-labs/devcodex.
- SKILL.md
- agents/openai.yaml
- repair-prevention-assessment.schema.json
Open the folder on GitHubat commit 1dd4525
Compare with similar skills
Rework Prevention Engineering next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Rework Prevention Engineering this skilldevcodex-labs/devcodex | 439 | — | ~1.6k | Automated safety check: Pass | AGPL-3.0 | |
| Agile Product Ownerdavila7/claude-code-templates | 32k | 2 repos | ~256 | Automated safety check: Pass | MIT | |
| Implementing Network Intrusion Prevention With Suricatamukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~3k | Automated safety check: Notes | Apache-2.0 | |
| Monte Carlo Preventsickn33/agentic-awesome-skills | 47k | 1 repos | ~3.3k | Automated safety check: Pass | MIT | |
| Agile Product Owneralirezarezvani/claude-skills | 28k | 3 repos | ~3.2k | Automated safety check: Pass | MIT | |
| Antipattern Preventiondoorkeeper-gem/doorkeeper | 5.5k | — | ~1.1k | Automated safety check: Pass | MIT |
Similar skills
Implementing Network Intrusion Prevention With Suricata
mukul975/Anthropic-Cybersecurity-Skills
Deploys and configures Suricata as an inline network intrusion prevention system, covering IPS mode setup (NFQueue), custom rule writing, Emerging Threats ruleset management, performance tuning, and…
Monte Carlo Prevent
sickn33/agentic-awesome-skills
Surfaces Monte Carlo data observability context (table health, alerts, lineage, blast radius) before SQL/dbt edits.
Agile Product Owner
alirezarezvani/claude-skills
Writes INVEST-checked user stories with acceptance criteria, splits epics, plans sprints from velocity and ranks the backlog with a weighted score.
Antipattern Prevention
doorkeeper-gem/doorkeeper
Avoid common Ruby and Rails antipatterns that degrade maintainability and performance.
Implementing Data Loss Prevention With Microsoft Purview
mukul975/Anthropic-Cybersecurity-Skills
Implements DLP policies using Microsoft Purview PowerShell cmdlets and the Graph API to protect data across Exchange Online, SharePoint, OneDrive, Teams, endpoints, and Power BI, including…
More from devcodex-labs/devcodex
All 70 skills in this repoAccessibility I18n
devcodex-labs/devcodex
无障碍与国际化专家 Owner — 当任务涉及可访问性、键盘操作、焦点、屏幕阅读器、ARIA、语言地区、本地化、RTL、翻译资源、用户可见文案或多语言文档时使用；要求把包容性体验和本地化验证绑定到真实用户路径。
AI Agent System Architecture
devcodex-labs/devcodex
AI Agent 系统架构专家 Owner — 当任务涉及 Agent 路由、工具调用、上下文管理、记忆、状态机、权限、人机协作、可观测性、回放验证或模型辅助治理时使用；要求把 Agent 行为设计成可解释、可恢复、可审计。
API Contract Architecture
devcodex-labs/devcodex
API 契约架构专家 Owner — 当任务涉及 public API、HTTP/SDK/CLI 契约、版本兼容、错误模型、分页过滤、幂等、Schema、类型、迁移或消费者影响时使用；要求先冻结消费者契约，再设计实现与验证。
Architecture Design
devcodex-labs/devcodex
架构设计文档编排 Owner — 当用户要求架构设计、系统设计、技术架构或可指导开发、Review 与任务拆分的完整方案时使用；要求从业务流程反推节点、状态、数据、一致性、异常补偿、ADR 与实施任务。
Audit Common
devcodex-labs/devcodex
审查公共维度 G0~G5 + Profile Freshness Check — 所有 audit 子类型必先执行的基础维度层
Audit Session
devcodex-labs/devcodex
审计工作流的跨会话状态机 — 在 <audit-root/.audit-state/<session-id.json 持久化轮次/发现项/收敛状态，支持 Token 中断后精准恢复
Questions about Rework Prevention Engineering
What does Rework Prevention Engineering do?
返工预防工程 Owner — 当任务涉及返工率、一次通过率、反复返修、复审持续出现新问题、重复逃逸、whyMissed 复发、预防措施有效性或希望把问题发现前移时使用；要求区分返工与需求变化，建立可比较基线，并用后续任务的前瞻证据验证控制是否有效。. Rework Prevention Engineering is an agent skill from devcodex-labs/devcodex.
How do I install Rework Prevention Engineering in Claude Code?
Run `npx skills add devcodex-labs/devcodex --skill rework-prevention-engineering -a claude-code`. Or copy the skill folder (content/skills/rework-prevention-engineering in devcodex-labs/devcodex) into .claude/skills/rework-prevention-engineering in your project. Claude Code loads it when a task matches its description.
How do I install Rework Prevention Engineering in Codex?
Run `npx skills add devcodex-labs/devcodex --skill rework-prevention-engineering -a codex`. Or copy the skill folder (content/skills/rework-prevention-engineering in devcodex-labs/devcodex) into .agents/skills/rework-prevention-engineering in your project. Codex loads it when a task matches its description.
Can I use Rework Prevention Engineering in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add devcodex-labs/devcodex --skill rework-prevention-engineering -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/rework-prevention-engineering, .gemini/skills/rework-prevention-engineering, .github/skills/rework-prevention-engineering and .opencode/skills/rework-prevention-engineering in your project.
What does Rework Prevention Engineering need to run?
SKILL.md names no scripts, command-line tools or credentials: Rework Prevention Engineering is instructions for the agent only.
Does Rework Prevention Engineering access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Rework Prevention Engineering safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Rework Prevention Engineering use?
Rework Prevention Engineering is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Rework Prevention Engineering use?
About 1.6k tokens (SKILL.md is roughly 6.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Rework Prevention Engineering?
Skills that share tags, products or a category with Rework Prevention Engineering: Agile Product Owner (davila7/claude-code-templates, 32k stars), Implementing Network Intrusion Prevention With Suricata (mukul975/Anthropic-Cybersecurity-Skills, 34k stars), Monte Carlo Prevent (sickn33/agentic-awesome-skills, 47k stars) and Agile Product Owner (alirezarezvani/claude-skills, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Rework Prevention Engineering?
devcodex-labs (a GitHub organization) maintains it in devcodex-labs/devcodex, which has 439 GitHub stars. The repository holds 70 skills in this directory. The repository was last updated on September 17, 2026.
Source: devcodex-labs/devcodex on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.