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/w693847022/memory_service/code-implementationnpx skills add w693847022/memory_service --skill code-implementationgit clone --depth 1 https://github.com/w693847022/memory_serviceWhat 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 | $0.02812 |
| Opus 5 | $0.00016 | $0.01406 |
| Sonnet 5 | $0.00006 | $0.00562 |
| Haiku 4.5 | $0.00003 | $0.00281 |
Grade A, and why
code-implementation 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 yesterday.
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 — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.
代码实现与测试技能
参数规范
| 参数 | 说明 | 要求 |
|---|---|---|
item_id |
已存在的 feature 或 fix ID | 必需 |
--plan |
直接提供完整修改方案(可选) | 可选,不提供则从 memory_mcp 查询 |
参数规则:
- 无参数时:拒绝执行
- 仅提供
item_id:从 item_id 记录的 content 和关联 item 中获取完整修改方案 - 提供
--plan:使用用户提供的方案,跳过 memory_mcp 查询
前置条件
必需前置条件
item_id必须存在(features 或 fixes 分组)- 必须存在以下之一:
- 方式1(推荐): item_id 记录的 content 或关联 item 中包含完整修改方案
- 方式2: 用户通过
--plan参数或交互式输入提供完整修改方案
Git 分支要求
- 当前分支不能是
main或master - 分支必须是干净的(无未提交的更改)
- 如果不满足,技能将拒绝执行并提示用户
完整修改方案格式要求
# <item_id> 实现方案
## 需求/问题描述
[完整的需求或 bug 描述]
## 代码修改计划
### 修改的文件列表
- `path/to/file1.ts`: 修改说明
- `path/to/file2.ts`: 修改说明
### 具体修改内容
[详细的代码修改方案,包括函数签名、逻辑变更等]
## 测试计划
### 单元测试
- [ ] 测试场景1: 描述
- [ ] 测试场景2: 描述
### 整合测试
- [ ] 测试场景1: 描述
⚠️ 重要指令
DO NOT ENTER PLAN MODE - 此技能要求直接执行实现方案,不进入计划模式
使用子代理处理 memory_mcp 和文件操作 - 以下操作通过 Agent 工具执行,减少主窗口上下文污染:
- 所有
mcp__memory_mcp__*工具调用 - 所有文件操作:
Read、Edit、Write、Glob、Grep
循环计数 - 所有循环重试最多3次,超限后暂停并请求用户介入
提醒用户使用 auto 模式 - 技能开始时提醒用户可使用 auto 模式提高效率
初始化阶段
步骤 1: 参数验证与方案获取
-
验证 item_id 并获取记录
- 使用子代理查询 memory_mcp,获取
item_id的完整记录(features 或 fixes 分组) - 如果不存在,拒绝执行并提示
- 使用子代理查询 memory_mcp,获取
-
获取完整修改方案(按优先级尝试)
方式1: 从 item_id 记录的 content 中获取
- 检查 item_id 的 content 字段是否包含完整的修改方案
- 如果包含,验证方案格式是否完整(包含代码修改计划和测试计划)
方式2: 从关联 item 中获取
- 如果 content 中没有完整方案,检查
related字段 - 遍历关联的 item_id,查询其 content
- 查找包含完整修改方案的关联 item
- 如果找到,使用该方案
方式3: 使用用户提供的方案
- 如果以上方式均未找到,检查是否提供了
--plan参数 - 使用用户提供的方案,验证格式完整性
-
方案获取失败处理
- 如果所有方式都无法获取完整修改方案,拒绝执行并提示:
错误: 无法获取完整修改方案 请确保以下之一: 1. item_id 的 content 包含完整修改方案 2. 关联 item 的 content 包含完整修改方案 3. 使用 --plan 参数提供方案
- 如果所有方式都无法获取完整修改方案,拒绝执行并提示:
步骤 2: Git 分支检查
- 检查当前分支
git branch --show-current- 如果是
main或master,拒绝执行并提示:错误: 当前在 main/master 分支上 请先创建并切换到开发分支,例如: git checkout -b feature/<item_id> git checkout -b fix/<item_id>
- 如果是
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.
- yesterday First seen · 380 lines · 32 tokens per session scan A 42c08637f58c
code-implementation is a skill published in the GitHub repository w693847022/memory_service (1 stars, last pushed 3mo ago), licensed MIT. It adds 32 tokens to every session and 2,812 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…