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/magic3007/dotfiles/save-pipeline-memorynpx skills add magic3007/dotfiles --skill save-pipeline-memorygit clone --depth 1 https://github.com/magic3007/dotfilesWrote 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/magic3007/dotfiles/save-pipeline-memory)<a href="https://agentmods.dev/skills/magic3007/dotfiles/save-pipeline-memory"><img src="https://agentmods.dev/badge/skills/magic3007/dotfiles/save-pipeline-memory.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 | $0.00154 | $0.02121 |
| Opus 5 | $0.00077 | $0.01060 |
| Sonnet 5 | $0.00031 | $0.00424 |
| Haiku 4.5 | $0.00015 | $0.00212 |
Grade A, and why
save-pipeline-memory 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Save Pipeline Memory
在经历多轮试错之后，把最终跑通的工作流固化下来。核心产出两样东西：
- 可执行的脚本 — 最终能跑通的命令，封装为接受参数的脚本，别人拿到就能跑
- Pipeline Memory 文档 — 干净的可复现步骤 + 弯路经验的分离记录
本 skill 是通用方案，不绑定任何特定项目、工具或环境。
脚本优先原则（最高优先级）
能用脚本固化的地方，必须写脚本。Pipeline Memory 的 Pipeline 节不允许出现裸命令。
这是本 skill 最核心的约束，优先级高于其他所有规则。
判断标准
| 情况 | 做法 |
|---|---|
| 步骤需要反复执行 | 必须写脚本 |
| 步骤有参数需要传递 | 必须写脚本（接受 CLI 参数） |
| 步骤依赖配置文件 | 必须写脚本（从配置自动读取，不硬编码） |
| 步骤有多个子步骤 | 必须写脚本（编排子步骤） |
| 步骤涉及多个工具/命令的串联 | 必须写脚本（固化管道逻辑） |
| 一次性、纯交互式、无法复现的操作 | 可以只记录操作说明（极少见） |
反面例子（❌ 不允许出现在 Pipeline Memory 的 Pipeline 节）
# 裸命令 — 参数散落、无法复现、换人换环境就跑不了
vela submit --model-id 204737 --snippet-id 7047 --data /path/to/data.jsonl
python some_script.py --input /hardcoded/path/data.jsonl --output /hardcoded/path/out/
正面例子（✅ 要求的形式）
# 脚本调用 — 参数化、可复现、换人换数据都能跑
bash scripts/submit_eval.sh --config exprs/v1/config.yaml
python scripts/run_pipeline.py --data ./input.jsonl --output ./results/
脚本内部从 config 文件读取可推导值（模型 ID、路径前缀等），只暴露真正需要用户决策的参数。
核心理念
试错过程 最终产出
───────── ────────
手拼命令 → 失败 ✅ 脚本（可重复运行）
改参数 → 失败 📝 Pipeline Memory（可复现步骤）
再试 → 成功 💡 弯路经验（避免重蹈覆辙）
- 脚本化是终点：最终 pipeline 里的每一步必须是一个脚本调用，不是手拼的裸命令。 脚本接受参数、不硬编码路径、从配置文件自动读取可推导值。
- 主角与配角分离：成功路径放进 "✅ Pipeline"，试错过程放进 "💡 弯路与经验"。
- 脚本即文档：一个好的脚本比十段文字描述更能说明工作流。宁可多花 10 分钟写脚本，也不要留下一段裸命令让人猜。
两层存储
| 层级 | 文件 | 何时加载 | 内容 |
|---|---|---|---|
| 探索快照 | pipeline_memory/YYYY-MM-DD_HHMM_<描述>.md |
不自动加载 | 完整记录（含弯路） |
| 定稿 pipeline | pipeline_memory/PIPELINE.md |
通过 CLAUDE.md 自动加载 |
只含干净的最终步骤 |
工作流程
第 1 步：确定保存位置
- 用户传入的路径参数（如
/save-pipeline-memory ~/my-project） - 若未传参，检查当前目录下是否已有
pipeline_memory/ - 都没有，用
<cwd>/pipeline_memory/，先告知用户
第 2 步：提取脚本（核心步骤，不可跳过）
回顾 session 中最终跑通的命令，将其改写为可执行脚本，保存到合适的位置（项目 scripts/ 或 pipeline_memory/scripts/）。
这是本 skill 最关键的一步。不要跳过，不要偷懒。 如果你发现自己在 Pipeline Memory 里写裸命令，停下来，先去写脚本。
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 · 155 lines · 154 tokens per session scan A 7a171f43f2ad
save-pipeline-memory is a skill published in the GitHub repository magic3007/dotfiles (11 stars, last pushed yesterday), licensed MIT. It adds 154 tokens to every session and 2,121 once invoked, about $0.0008 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
save-memory
Export and distill the current conversation into a memory file. Use when the user asks to save, remember, or note the current session for future context.
Context Optimization
Techniques to maximize context window efficiency, reduce latency, and prevent 'lost in middle' issues through strategic masking and compaction.
obsidian
Find, navigate, read, and edit notes in the user's personal Obsidian vault (an iCloud-synced markdown collection on macOS). Use whenever the user mentions "the vault", "my notes", "Obsidian", a daily note, a meeting note, scratchpad, or asks to look up/jot down something that sounds personal-knowledge-base-like (e.g.…
consolidate
Audit and prune rules/skills/learnings to prevent context bloat. Triggers "consolidate", "clean up rules", "spa day", "what's redundant", degraded agent perf.
git-commit
Create a new git commit for staged changes. Use when the user asks to commit staged changes with an auto-generated Conventional Commits message, or when Claude Code itself wants to run git commit.
github-pr-create
Create a pull request with an auto-generated description. Use when the user asks to open a PR for the current branch's changes.