What is memory-pipeline?

An automatic memory pipeline for agent conversations and projects. It retrieves relevant past context, saves unfinished work as drafts, and publishes memories when a task is complete.

Use it to recall project history, track whether work has converged, save draft memories, and publish completed memories with source markers.

It helps agents use earlier decisions and preserve useful results instead of losing context between turns or sessions.

memory-pipeline — Skill for Claude Code and Codex by ysydhc

Install

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.

Any agent

npx skills add ysydhc/team_memory --skill hermes_memory_pipeline

Clone the repo

git clone --depth 1 https://github.com/ysydhc/team_memory

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ysydhc/team_memory/hermes_memory_pipeline/github.svg)](https://agentmods.dev/skills/ysydhc/team_memory/hermes_memory_pipeline)

Your own site

<a href="https://agentmods.dev/skills/ysydhc/team_memory/hermes_memory_pipeline"><img src="https://agentmods.dev/badge/skills/ysydhc/team_memory/hermes_memory_pipeline/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ysydhc/team_memory/hermes_memory_pipeline"><img src="https://agentmods.dev/badge/skills/ysydhc/team_memory/hermes_memory_pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 557 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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 5.1	$0.00031	$0.00557
Opus 5.5	$0.00012	$0.00223
Sonnet 5.5	$0.00006	$0.00111
Haiku 4.5	$0.00003	$0.00056

Measured 5d ago against content hash a9b0e3ac969f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

memory-pipeline 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 5d 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.

scripts/hooks/hermes_memory_pipeline_skill.md · 62 lines

What it actually says

Hermes 记忆管线

触发条件

每轮对话自动执行（不需要用户手动调用）

执行步骤

步骤 1：自动检索

每轮对话开始时，根据用户消息判断是否需要检索记忆：

如果用户消息包含关键词（"之前"/"上次"/"经验"/"踩坑"/"remember"/"previously"） → 调用 TM MCP 的 memory_recall 工具进行全量检索
否则 → 调用 TM MCP 的 memory_context 工具获取项目级上下文

步骤 2：标注记忆来源

在回复中引用检索到的记忆时，必须保留 [mem:xxx] 标记：

正确："根据你之前的经验 [mem:exp-a1b2]，Docker 网络用 TUN 模式"
错误："根据你之前的经验，Docker 网络用 TUN 模式"（丢失了标记）

这个标记用于评估系统自动判定记忆是否被使用。

步骤 3：收敛检测

在以下情况判断当前任务已收敛：

用户说"解决了"/"完成了"/"先这样"/"搞定"
执行了 git commit
执行了测试且通过

步骤 4：草稿写入

收敛时 → 调用 TM MCP 的 memory_draft_publish 发布草稿未收敛 → 调用 TM MCP 的 memory_draft_save 保存草稿

步骤 5：会话结束

会话结束时，如果有未发布的草稿 → 强制发布

管线脚本

Hermes 可以直接调用 hermes_pipeline.py 脚本：

on_turn_start(user_message, project) → 检索记忆
on_turn_end(session_id, agent_response, project, recent_tools) → 更新草稿
on_session_end(session_id) → 强制发布

评估

系统自动通过 [mem:xxx] 标记评估记忆使用情况：

使用率 > 40% → 系统有效
使用率 20-40% → 需要调整
使用率 < 20% → 系统无效

Changes

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.

5d ago First seen · 62 lines · 31 tokens per session scan A a9b0e3ac969f

Subscribe to this mod's changes

memory-pipeline is a skill published in the GitHub repository ysydhc/team_memory (1 stars, last pushed 6d ago), licensed MIT. It adds 31 tokens to every session and 557 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-11-03.

Memory and context

memory-pipeline next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
memory-pipelineysydhc/team_memory	Skill	1	6d ago	MIT	A	31	Claude Code, Codex
knowledge-ingestopenclaw/openclaw	Skill	394k	today	MIT	A	80	Claude Code, Codex
mem0-oss-to-platformmem0ai/mem0	Skill	69k	2d ago	Apache-2.0	A	217	Claude Code, Codex
forgetasgeirtj/system_prompts_leaks	Skill	71k	today	CC0-1.0	A	0	Claude Code, Codex
Cortexdanielmiessler/LifeOS	Skill	20k	3d ago	MIT	A	184	Claude Code
memoryopensquilla/opensquilla	Skill	7.1k	2d ago	Apache-2.0	A	44	Claude Code, Codex
ha-data-storesshiwenwen/hope-agent	Skill	1.9k	today	MIT	A	115	Claude Code, Codex