Memtrace Cochange
syncable-dev/memtrace-public
Find files that historically co-change with a target symbol or file, ranked by co-occurrence across git episodes.
SOP for terminal-based, git-native AI pair programming with Aider (git work-tree + tree-sitter repo-map + edit-format + human-in-loop REPL).
$ npx skills add agentsope/SkillAlchemy --skill agentsop-aider -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install agentsope/SkillAlchemy agentsop-aider --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/agentsope/SkillAlchemy.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/agentsop-aider .claude/skills/agentsop-aider && 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 "agentsop-aider" agent skill from https://github.com/agentsope/SkillAlchemy/tree/master/skills/agentsop-aider into .claude/skills/agentsop-aider/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentsop-aider", 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/agentsope/SkillAlchemy/tree/master/skills/agentsop-aiderType 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 agentsope/SkillAlchemy --skill agentsop-aider -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install agentsope/SkillAlchemy agentsop-aider --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agentsope/SkillAlchemy.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/agentsop-aider .agents/skills/agentsop-aider && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "agentsop-aider" agent skill from https://github.com/agentsope/SkillAlchemy/tree/master/skills/agentsop-aider into .agents/skills/agentsop-aider/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentsop-aider", 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 agentsope/SkillAlchemy --skill agentsop-aider -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install agentsope/SkillAlchemy agentsop-aider --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agentsope/SkillAlchemy.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/agentsop-aider .cursor/skills/agentsop-aider && 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 "agentsop-aider" agent skill from https://github.com/agentsope/SkillAlchemy/tree/master/skills/agentsop-aider into .cursor/skills/agentsop-aider/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentsop-aider", 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/agentsope/SkillAlchemy.git --path skills/agentsop-aider--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 agentsope/SkillAlchemy --skill agentsop-aider -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install agentsope/SkillAlchemy agentsop-aider --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agentsope/SkillAlchemy.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/agentsop-aider .gemini/skills/agentsop-aider && 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 "agentsop-aider" agent skill from https://github.com/agentsope/SkillAlchemy/tree/master/skills/agentsop-aider into .gemini/skills/agentsop-aider/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentsop-aider", 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 agentsope/SkillAlchemy agentsop-aiderInstalls 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 agentsope/SkillAlchemy --skill agentsop-aider -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/agentsope/SkillAlchemy.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/agentsop-aider .github/skills/agentsop-aider && 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 "agentsop-aider" agent skill from https://github.com/agentsope/SkillAlchemy/tree/master/skills/agentsop-aider into .github/skills/agentsop-aider/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentsop-aider", 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 agentsope/SkillAlchemy --skill agentsop-aider -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install agentsope/SkillAlchemy agentsop-aider --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agentsope/SkillAlchemy.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/agentsop-aider .opencode/skills/agentsop-aider && 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 "agentsop-aider" agent skill from https://github.com/agentsope/SkillAlchemy/tree/master/skills/agentsop-aider into .opencode/skills/agentsop-aider/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentsop-aider", 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.
agentsop-aiderSOP for terminal-based, git-native AI pair programming with Aider (git work-tree + tree-sitter repo-map + edit-format + human-in-loop REPL).
Agentsop Aider is an agent skill from agentsope/SkillAlchemy. SOP for terminal-based, git-native AI pair programming with Aider (git work-tree + tree-sitter repo-map + edit-format + human-in-loop REPL). Use when editing code in an existing git repo via an LLM, when you need to converge a change to 2-5 files, pick an edit format that fits the model, run architect+editor mode, or wire an auto-test loop.
Its SKILL.md is about 3.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 9 other files, including reference files (for example `README.md`, `intermediate/operation_candidates.json` and `references/R1-architecture.md`).
It sits in Development, covering Codebase onboarding, Operations and SOPs and Git workflow. It works with Git. The repository describes itself as: From thought to skill. From signal to structure. The licence is MIT.
7 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit d0f0355. It shows what the files ask for, not the result of running them.
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.
Shell commands in SKILL.md call:
gitFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Agentsop Aider loads about 3.5k tokens when it runs, and up to ~12k if it reads all its reference files. Until then it costs about 89 tokens; SKILL.md has 982 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.
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.
The full file from agentsope/SkillAlchemy at commit d0f0355, republished under its MIT licence (© agentsope). 982 words, ~3,461 tokens.
.claude/skills/agentsop-aider/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.一句话:Aider 是“git 工作树 + tree-sitter 仓库地图 + 编辑格式 + 人类在环 REPL”的四元组。理解这四个原语,剩下的都是配置。
下列任一情形成立时,按本 SOP 进入 Aider 工作模式:
/ask 让模型借助 repo-map 把范围找出来。/undo 一步回退)。不应激活的反面信号:见 §6 反模式与边界。
+------------------+ +------------------+ +------------------+ +------------------+
| 1. Git working | | 2. Tree-sitter | | 3. Edit format | | 4. REPL loop |
| tree | | repo-map | | (wire proto) | | (你在环里) |
| | | | | | | |
| - per-edit | | - symbol-level | | - diff / udiff | | - /ask /code |
| commit | | summary | | / whole / | | /architect |
| - /undo | | - PageRank over | | patch | | - 每轮人手确认 |
| - dirty 文件 | | import graph | | - 模型适配选择 | | - 不自主 |
| 先 commit 再编 | | - 动态预算 | | - JSON 是反模式 | | |
+------------------+ +------------------+ +------------------+ +------------------+四者缺一不可:
| 层 | 内容 | 谁能改 |
|---|---|---|
| 系统提示 + 编辑格式说明 | Aider 固化 | Aider |
| 只读上下文 | repo-map + /read 文件 + CONVENTIONS.md | 你(通过 --read) |
| 读写上下文 | /add 的文件 | LLM 只能编辑这里的文件 |
铁律:LLM 只允许编辑
/add-ed 的文件。这是 Aider 的安全边界。模型“改错了文件”几乎总是因为该文件没/add或你/add了太多无关文件。
"Above about 25k tokens of context, most models start to become distracted." [aider.chat/docs/troubleshooting/edit-errors.html]
把这条当硬约束:超过 25k tokens,编辑准确率断崖式下降。/tokens 持续监控。
repo-map 是 tree-sitter 提取的符号清单(类、函数、签名),用 PageRank 在源文件依赖图上排序,塞给 LLM 当地图。这不是 embedding 检索。
为什么不用 embeddings:
/map 可以打印出来人工审计,向量做不到。预算是动态的:你不 /add 任何文件时,map 占用大;/add 了正确文件后,map 自动缩小,省下的 token 给真正的代码。
| 格式 | 谁用 | 强项 | 弱项 |
|---|---|---|---|
whole | 弱模型 / GPT-3.5 / 应急回退 | 解析最稳,无 merge 错误 | 贵;4k 输出上限会截断 |
diff (SEARCH/REPLACE) | GPT-4o, Sonnet, 多数强模型 | token 高效 | SEARCH 块必须字节匹配 |
diff-fenced | Gemini 系列 | 路径放在 fence 内 | 非主流 |
udiff | GPT-4 Turbo (1106) | 模仿 patch 程序的严格性,降低 laziness | 提示更重 |
patch | GPT-4.1 (OpenAI patch 协议) | 多动作鲁棒 | 模型特定 |
editor-diff / editor-whole | architect 模式的 editor 子模型 | 提示更瘦,专注编辑 | 仅在 architect 下有意义 |
Aider 已经对常见模型选好默认值;只有出现编辑错误时才覆盖。
⇒ 不要把代码编辑包进 JSON tool-call。所有模型在 Aider 的实测里都因此变差,包括 Sonnet(详见 §5 案例 6 与引文)。
# 0. 在 git 仓库根目录。stash 或 commit 在途修改。
git status
# 1. 选模型(榜单当前前列:gpt-5, claude-3.7-sonnet, o3-pro, gemini-2.5-pro)
# [aider.chat/docs/leaderboards/]
# 2. 最小启动 — 让 repo-map 帮 LLM 自己找路
aider
# 3. 范围已知 — 直接预加 + 风格文件
aider src/auth.py tests/test_auth.py --read CONVENTIONS.md
# 4. 强思考 + 廉价编辑(architect 模式)
aider --architect --model o1-preview --editor-model gpt-4o
# 5. 自动测试回路
aider --test-cmd "pytest -x" --auto-test
# 6. 巨型 monorepo
cd packages/feature-foo && aider --subtree-only
# 并维护 .aiderignore/add 纪律)不知道改哪个文件?
→ /ask which files implement <feature>? (LLM 用 repo-map 回答)
→ /add 它命名的文件(只加这些)
知道改哪个文件?
→ 启动时 CLI 直接传,或 /add path/to/file.py
需要参考但不允许改的文件(schema, config, conventions)?
→ /read path/to/ref.md铁律重申:少 /add,敢 /drop。/tokens 看现状。
/ask → /code)> /ask 当前的 auth 怎么实现?如果改成 JWT 会有什么破坏?
< [模型基于 repo-map + 已 /add 的文件作答]
> /ask 那我们用 PyJWT 还是 authlib?给出权衡。
< [...]
> /code 按刚才讨论的方案,把 sessions 改成 JWT。
< [模型给出 diff]
[Aider 自动应用 → 自动 git commit]
> /test pytest
< [失败时模型看到输出并尝试修复]"Break your goal down into bite sized steps. Do them one at a time." [aider.chat/docs/usage/tips.html]
何时开启:你最好的 reasoner 编辑能力差(典型:o1-preview 单独跑 79.7%,搭配 Sonnet 当 editor 拉到 82.7% [aider.chat/2024/09/26/architect.html])。
| 组合 | Polyglot Pass@2 | 备注 |
|---|---|---|
| o1-preview (architect) + o1-mini (editor, whole) | 85% | SOTA 当时;慢,不适合交互 |
| o1-preview + Sonnet | 82.7% | "entirely practical" |
| Sonnet + Sonnet | 80.5% | 比单跑 77.4% 高 |
| GPT-4o + GPT-4o | 75.2% | 比单跑 71.4% 高 |
启用:--architect 或 /architect。Aider 自动把 editor 切到 editor-diff / editor-whole。
/lint # 默认 --auto-lint 已开
/test pytest -x # 失败时输出回填到 chat
/run npm run typecheck # 输出可选择性回填
/diff # 看上一轮的 diff"Aider will try and fix any errors if the command returns a non-zero exit code." [aider.chat/docs/usage/lint-test.html]
formatter 注意:把会重写文件并返回非零的 formatter 包装在双跑脚本里(第一遍 format,第二遍验证)。
| 症状 | 操作 |
|---|---|
/tokens > 25k | /drop 不再需要的文件 |
| 话题切换 | /clear(保留文件,清历史) |
| 想全新开始 | /reset(丢文件 + 清历史) |
| 模型反复改错文件 | /ls 检查;/drop 多余的;/add 缺的 |
| 反复 edit format 错误 | /clear;换模型;--edit-format whole 兜底 |
git log --oneline 看一次会话的提交链。git rebase -i HEAD~N(先保留中间 commit 当 undo 栈,最后压)。源:[aider.chat/docs/usage/commands.html]
/add <files> 把文件加入 chat(LLM 可编辑)
/read <file> 加为只读(LLM 不能编辑)
/drop <files> 从 chat 移除
/ls 列出已知文件 + 标注哪些在 chat 里
/ask <q> 只讨论,不动文件
/code <req> 明确要求改代码(不加前缀也行)
/architect <req> 双模型 architect+editor
/model <name> 切换主模型
/clear 清 chat 历史(保留文件)
/reset 丢文件 + 清历史
/tokens 当前 token 占用
/map 打印当前 repo-map
/diff 上一轮的 diff
/undo 回退最近一次 Aider commit
/commit 为 chat 外的改动生成 commit
/run <cmd> 跑命令,可选回填输出(别名 !)
/test <cmd> 跑测试,失败时回填
/web <url> 抓网页转 markdown 进 chat
/copy 复制最后一条回复
/help <q> 关于 Aider 本身的问题CLI 关键标志:
--model X 主模型
--editor-model Y editor 子模型(architect 用)
--edit-format whole|diff|udiff|patch
--editor-edit-format ... editor 子模型的格式
--architect 进入 architect 模式
--read FILE 只读上下文(可多次)
--map-tokens N repo-map 预算;N=0 关闭
--subtree-only 仅本子目录 + 子树
--auto-lint / --no-auto-lint
--test-cmd CMD --auto-test
--no-auto-commits 关掉自动提交(不建议)
--no-git 完全脱 git(失去安全保障)
--message "..." 一次性非交互模式(脚本/agent 用)
--yes 全部确认(脚本/agent 用)配置文件:.aider.conf.yml(持久 CLI 默认)、.aiderignore(排除 repo-map 路径)、CONVENTIONS.md(用 --read 加载)。
触发:LLM 改的不是你想改的文件,或编造路径。
诊断:LLM 只能安全编辑 /add 的文件。要么目标没 /add,要么 /add 太多导致干扰。
决策规则:
/ls 看现状。/add path/to/target.py。/drop 无关的。/ask which file implements X?,让 repo-map 替你答。为什么有效:/add-ed 文件就是写集合(write-set)。repo-map 只是可读地图,不是写集合。
触发:tokens 涨到 25–50k+,响应被截断,模型在 monorepo 上明显变笨。
决策规则(从最便宜的做起):
| 步 | 动作 |
|---|---|
| 1 | /tokens 看占用分布 |
| 2 | /drop 不再需要的文件 |
| 3 | /clear 清聊天历史(保留文件) |
| 4 | --map-tokens 1024(或弱模型 0) |
| 5 | monorepo:进子目录 + --subtree-only;加 .aiderignore |
| 6 | 拆任务:每个子任务一个会话 |
关键认知:不要“为了保险全 /add”。SWE-Bench 数据,只靠 repo-map Aider 仍然 70.3% 选对文件 [aider.chat/2024/05/22/swe-bench-lite.html]。
触发:Aider 报 “SEARCH block not found in file”。
诊断:模型给的 SEARCH 文本和文件字节不匹配(空白、前次失败后状态漂移、纯臆造)。
决策规则:
/tokens — 接近 25k 时合规率下降。/drop + /clear 减负。--edit-format whole。贵但稳。--architect —— 双步流程对“执行编辑指令”的依从性更高。历史教训:GPT-4 Turbo 上 unified-diff 把 refactor 基准从 20% 拉到 61%,并把 “lazy comment” 砍到 1/3 [aider.chat/2023/12/21/unified-diffs.html]。说明 格式工程的边际收益经常高于换模型。
触发:硬推理任务;你有 o1/o3(强 reasoner,但编辑差)。
决策规则:
| 情况 | 建议 |
|---|---|
| reasoner 编辑也干净(GPT-4o, Sonnet) | 不开 architect。单跑就行 |
| reasoner 编辑差(o1-preview 单跑 79.7%) | 开 architect:o1-preview + Sonnet → 82.7% |
| 追 SOTA、能等 | o1-preview + DeepSeek/o1-mini whole → 85%(慢,"probably not practical for interactive use") |
| 例行编辑 | 单跑更快更省 |
反直觉点:连 Sonnet 自配 editor 也涨(77.4 → 80.5%)。但 +3pp 是否值翻倍的 token 成本,取决于场景。
触发:Claude 3.5 Sonnet 回复在编辑中段截断。
诊断:Sonnet 倾向写太多——整文件 SEARCH/REPLACE 而不是最小 diff [aider.chat/2024/07/01/sonnet-not-lazy.html]。
决策规则:
触发:自建 agent 包 Aider 时考虑结构化 tool-call。
决策规则:不要把代码包进 JSON tool-call。
"All of the models did worse on the benchmark when asked to return code in a structured JSON response." [aider.chat/2024/08/14/code-in-json.html]
即便用 OpenAI strict mode 强制 JSON 合法,JSON 里的代码本身也劣化(更多 SyntaxError / IndentationError)。若 harness 必须 tool-call,把代码塞单一字符串字段,并预期质量损失。
| 场景 | 替代 |
|---|---|
| 从零起项目(无 git history、无现有代码) | Cursor 一类,或纯 LLM 对话 |
| 跨千个文件的机械重构 | 先用 sed / AST 工具 / IDE 重构;Aider 收尾语义部分 |
| 不能用 git 的工作流(Perforce-only、二进制资产) | 别用 Aider;它的安全保障建立在 git 之上 |
| 需要 IDE/浏览器感知(实时 diagnostics、devtools) | Cline / Continue / Cursor — Aider 看不到 IDE |
| 完全自主的 ticket→PR | OpenHands / Devin — Aider 是人在环设计 |
/add 求保险——反而干扰模型。/drop 才是常态操作。/map 看一下它已经知道什么。/clear——长会话历史漂移会让模型“记住错的东西”。话题切换就清。/undo 栈。正确做法是事后 git rebase -i 压。--read CONVENTIONS.md;formatter 返回非零会搞砸 auto-lint,用双跑脚本包一下。.aider.conf.yml、git history 本身)。| Aider | Cline | Cursor | Continue | OpenHands | |
|---|---|---|---|---|---|
| 表面 | 终端 REPL | VS Code 扩展 | 闭源 IDE(VS Code fork) | VS Code + JetBrains 扩展 | Web UI + Docker 沙箱 |
| 开源 | Apache 2.0 | 是 | 否 | 是 | MIT |
| 编辑原语 | diff/udiff/whole 文本 + git commit | tool-call + 每步人审 | 内嵌 Composer 多文件 | Edit/Chat/Agent/Autocomplete | 自主 plan→edit→test→PR |
| 上下文 | tree-sitter repo-map + 选择性 /add | 按需 tool-call 读 | 全仓库索引 | RAG | agentic 读 |
| 人审 | 每轮(/undo 兜底) | 每个 tool-call | 每次 Composer apply | 每次 edit | 无 |
| Git 集成 | 原生(每编辑一 commit) | 通过终端工具 | 手动 | 手动 | 沙箱里 PR |
| BYOM | 是(100+,经 LiteLLM) | 是 | 受限 | 是 | 是 |
来源:[frontman.sh/blog/best-open-source-ai-coding-tools-2026]、[cline.bot/blog/top-9-cursor-alternatives-in-2025]、[opensourcealternatives.to]、[shakudo.io/blog/best-ai-coding-assistants]。
--message、--yes、配置文件 → 子进程驱动友好。/map 检查、可复现、无向量库依赖。/undo;Cline 是事前 approve。即便你选别的前端,Aider 的公开实验是这些决定的参考:编辑格式选择(GPT-4 Turbo refactor 20%→61%)、repo-map 战胜 RAG(SWE-Bench Lite 70.3%)、architect+editor 拆分(79.7%→85%)、JSON-vs-text 劣化、lazy-coding 缓解——具体数据见前文各节。
© agentsope, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 7 other files (references) in skills/agentsop-aider of agentsope/SkillAlchemy.
Open the folder on GitHubat commit d0f0355
Agentsop Aider 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 |
|---|---|---|---|---|---|---|
| Agentsop Aider this skillagentsope/SkillAlchemy | 466 | — | ~3.5k | Automated safety check: Pass | MIT | |
| Memtrace Cochangesyncable-dev/memtrace-public | 489 | — | ~961 | Automated safety check: Pass | Custom licence | |
| Local File and Code Searchtaxueseek/argo | 186 | — | ~1.1k | Automated safety check: Pass | MIT | |
| basemind CLI Codebase NavigatorGoldziher/basemind | 108 | — | ~2k | Automated safety check: Pass | MIT | |
| Codewhale Contributor Onboardingcodewhale-hq/Codewhale | 41k | — | ~1.3k | Automated safety check: Pass | MIT | |
| Git Project Statusespennilsen/pi | 122 | — | ~4.4k | Automated safety check: Notes | MIT |
syncable-dev/memtrace-public
Find files that historically co-change with a target symbol or file, ranked by co-occurrence across git episodes.
taxueseek/argo
Searches local files and code through one script, seek.py, that picks between rg, fd and macOS Spotlight and works in three layers: locate, context, close reading.
Goldziher/basemind
Drives the basemind code-intelligence tool from the command line for symbol search, callers, git history and blame, document search and web crawling, sharing its cache with the MCP server.
codewhale-hq/Codewhale
Reports whether a fresh Codewhale checkout is current, builds and passes its tests, and what changed since the contributor was last here, without touching the working tree.
espennilsen/pi
Generate comprehensive status reports for git repositories. An agent skill from espennilsen/pi.
k1ein-chen/Harness-Starter
将当前会话中的技术决策、运维流程或阶段性研发进展,归档为标准工程文档(ADR / SOP / Handover),并自动更新模块内的 README 归档索引。
agentsope/SkillAlchemy
Coder-agent working-file budget discipline: keep the editable working set (files you /add into writable context) under ~25k tokens, separate "read" from "edit", delegate breadth to a read-only…
agentsope/SkillAlchemy
Split a multi-call LM workflow by cognitive load, not by accuracy: let one strong model make the few reasoning decisions and a cheap model do the many mechanical executions (Aider architect+editor…
agentsope/SkillAlchemy
SOP for building multi-agent systems with CrewAI — role-based collaboration, sequential/hierarchical processes, Flows, memory, delegation.
agentsope/SkillAlchemy
SOP for building LLM applications on Dify — visual workflow + chatflow + agent + RAG knowledge base + plugin marketplace + observability, self-hostable.
agentsope/SkillAlchemy
Designs multiscale chunking for RAG by embedding small units for retrieval precision and returning larger context for synthesis.
agentsope/SkillAlchemy
Enhancement-overlay skill — the DECISION + WIRING layer for LM observability that the single-backend skills [[langsmith]], [[phoenix]], [[mlflow]] do NOT cover.
Works with
Categories
SOP for terminal-based, git-native AI pair programming with Aider (git work-tree + tree-sitter repo-map + edit-format + human-in-loop REPL). Agentsop Aider is an agent skill from agentsope/SkillAlchemy. SOP for terminal-based, git-native AI pair programming with Aider (git work-tree + tree-sitter repo-map + edit-format + human-in-loop REPL).
Agentsop Aider fits situations like: editing code in an existing git repo via an LLM; you need to converge a change to 2-5 files; pick an edit format that fits the model; run architect+editor mode.
Run `npx skills add agentsope/SkillAlchemy --skill agentsop-aider -a claude-code`. Or copy the skill folder (skills/agentsop-aider in agentsope/SkillAlchemy) into .claude/skills/agentsop-aider in your project. Claude Code loads it when a task matches its description.
Run `npx skills add agentsope/SkillAlchemy --skill agentsop-aider -a codex`. Or copy the skill folder (skills/agentsop-aider in agentsope/SkillAlchemy) into .agents/skills/agentsop-aider in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add agentsope/SkillAlchemy --skill agentsop-aider -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agentsop-aider, .gemini/skills/agentsop-aider, .github/skills/agentsop-aider and .opencode/skills/agentsop-aider in your project.
Going by SKILL.md and its folder, Agentsop Aider needs the command-line tools its instructions call (git).
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
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.
Agentsop Aider is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.5k tokens (SKILL.md is roughly 14k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 8.7k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Agentsop Aider: Memtrace Cochange (syncable-dev/memtrace-public, 489 stars), Local File and Code Search (taxueseek/argo, 186 stars), basemind CLI Codebase Navigator (Goldziher/basemind, 108 stars) and Codewhale Contributor Onboarding (codewhale-hq/Codewhale, 41k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
agentsope (a GitHub user) maintains it in agentsope/SkillAlchemy, which has 466 GitHub stars. The repository holds 46 skills in this directory. The repository was last updated on October 9, 2026.
Source: agentsope/SkillAlchemy on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.