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/asherzj/ashers-agent-skills/implementnpx skills add asherzj/ashers-agent-skills --skill implementgit clone --depth 1 https://github.com/asherzj/ashers-agent-skillsWrote 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/asherzj/ashers-agent-skills/implement)<a href="https://agentmods.dev/skills/asherzj/ashers-agent-skills/implement"><img src="https://agentmods.dev/badge/skills/asherzj/ashers-agent-skills/implement.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 | $0.00047 | $0.01555 |
| Opus 5 | $0.00023 | $0.00777 |
| Sonnet 5 | $0.00009 | $0.00311 |
| Haiku 4.5 | $0.00005 | $0.00155 |
Grade A, and why
implement 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
实现并交付一张工单
实现用户在一份 spec(规格说明)或一张工单中描述的工作。一张工单是一次实现、验证、评审、提交和推送的最小交付单元;不要把多张工单揉进同一个提交。
用户显式调用本 Skill,或明确要求“交付”“提交并推送”,可视为提交与推送授权;模型自动选择的上层流程不能替代用户授权。这项授权不自动包含合并 PR、强制推送、改写远端历史或关闭工单;这些动作仍受用户要求和工单系统规则约束。
开始前
- 读取仓库的
AGENTS.md,以及已配置的工单系统、领域文档和相关 ADR。 - 完整读取 spec 或工单的正文与评论,提取验收用例、验收接缝、验收标准、范围外事项、架构约束、临时结构退出条件和交付证据。信息不足以安全实现时,先补齐缺口,不要自行发明需求。
- 检查当前分支、默认分支、远端和工作树状态。保留所有既有及无关改动;如果存在无法归属的修改,先停下并报告。
- 如果当前位于默认分支,先创建工单级分支再编辑。除非用户明确要求,否则禁止直接提交或推送到默认分支。
如果并行实现多张工单,每张工单必须使用独立分支和隔离的 git worktree;多个 agent 不得共享可写 checkout。无法隔离时改为顺序执行,完成一张工单的提交与推送周期后再开始下一张。
验收外循环
对功能行为先建立验收外循环,再进入内部实现:
- 选择当前工单负责的一个验收用例,从已约定的最高稳定接缝运行或编写它。
- 在新增能力尚不存在时,先确认验收测试因预期原因失败。如果它已经通过,先调查功能是否已存在、用例是否无效或接缝是否选错,不为满足仪式制造失败。
- 一次只推进一个验收用例或一个行为切片;不要先批量写完全部测试再实现全部代码。
- 无法可靠自动化的视觉、运维或第三方场景,提前记录可重复的人工验收步骤和证据,不伪造自动化覆盖。
验收测试只观察接口承诺。数据库、网络或外部服务失败时,在模块验收层测试对外错误、状态不变量和重试语义;在 Adapter 集成层使用真实依赖验证底层错误转换。只在系统边界使用 Mock 或故障注入,不 Mock 自有内部协作者。
实现与分层验证
- 在适用且已约定的测试接缝处,加载并完整遵循
tddSkill;用一个测试 → 一个最小实现的纵向切片让当前验收用例逐步转绿,不要写死特定客户端的 slash command。 - 单元或模块测试只覆盖复杂局部规则;集成测试覆盖真实数据库、Schema、协议和 Adapter;系统级测试只证明必须跨进程或跨界面接通的关键路径。不要让每层重复同一事实。
- 实现过程中反复运行当前验收测试、最相关的单个测试和类型检查。结束时运行本工单全部验收用例、完整测试套件、仓库已有的架构/契约检查和其他必要验证。
- 工单改变公共接口、跨上下文契约或依赖方向时,新增或更新相应的机器检查;如果仓库尚无这种检查,在交付证据中说明缺口并提出后续工单,只在用户或仓库流程授权时发布,不能声称架构约束已自动保护。
- 任何必需检查无法运行时,按阻塞处理;只有用户或仓库规则明确允许替代验证时,才执行当前最强的可用替代并说明差异。
- 满足验收标准后,以本工单分支的固定基点和原始 spec/工单为输入,加载并完整遵循
code-reviewSkill。修复阻塞性交付的问题并重新验证。
完成工单
只有在验收用例、验收标准、必要测试、架构检查和评审都通过后,才能进入本阶段。任何必需检查仍失败或受阻时,不得提交、推送或关闭工单;应报告准确的阻塞原因。
- 根据已确认的领域或架构变化,就地更新对应
CONTEXT.md、CONTEXT-MAP.md、ADR、接口契约或架构说明。不要把任务进度或实现细节写进领域词汇表。 - 检查临时兼容、Feature Flag、双写和旧接口是否已有明确删除条件与责任工单;当前工单负责删除时必须真的删除,不能只标记弃用。
- 检查分支、工作树状态和完整 diff。只暂存属于本工单的文件与删除项;在脏工作树中禁止使用
git add .、git add -A或git add --all。 - 创建一个带工单引用的简洁提交。提交后核对其完整内容,确认没有无关路径。
- 使用
git push -u origin HEAD推送当前工单分支。已按上文取得用户对提交与推送的授权时,无需再次进行对话确认,但工具或平台审批仍可能需要。除非用户明确要求,否则绝不强制推送。 - 如果推送被拒绝,立即停止。不得自动 rebase、merge、覆盖远端工作或关闭工单;报告本地 commit SHA 和拒绝原因。
- 推送成功后,验证远端分支和本地工作树。只有工单系统工作流授权实现 agent 收尾时,才发布完成证据并关闭工单。
- 如果本工单完成了仓库定义的完整功能或里程碑,执行
AGENTS.md或CLAUDE.md中规定的项目管理、变更日志或外部记录更新,再向用户报告完成。无法执行时明确阻塞,不得声称已经更新。
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 56 lines · 47 tokens per session scan A c0a6070b1b67
implement is a skill published in the GitHub repository asherzj/ashers-agent-skills (2 stars, last pushed 7d ago), licensed MIT. It adds 47 tokens to every session and 1,555 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
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for prisma-next. Use when the user wants to create a pull request, open a PR, or submit changes for review.
git-commit
Generate well-formatted git commit messages following conventional commit standards.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
commit-push-pr
Commit selected local changes, push the branch, and create or update a GitHub pull request with BitFun attribution. Use when the user asks to 提交 PR、提代码、commit and push、开 PR、create a pull request, or wants a Claude Code-like one-command PR publishing flow from BitFun.
commit
Commit current changes with a clear, descriptive message.
contributing
How to contribute to evlog, covering commit and PR conventions, changesets, the Definition of Done, testing rules, and the authored skills that walk through building a new adapter, enricher, framework integration, or map rule. Load this for any question about contributing, opening a PR, or adding something to the…