light-memory-pm

light-memory-pm is a skill for Claude Code from Light0305/Light-skills. It costs 368 tokens per session (10,175 once invoked), scanned A, original, MIT.

A project memory and management system that stores status, decisions, versions, agreed terms, and handoff notes in each project’s .light/ folder.

In plain words
What is it for?
It helps resume interrupted projects, record important decisions and releases, maintain a controlled glossary, calculate affected materials, and prepare handoffs.
Why use it?
It prevents long-running work from losing its context between conversations and keeps related documents aligned when definitions change.

Skill for Claude Code

Written for Claude Code: SessionStart hook event. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is [`docs/competitors/memory-pm.md`](../../docs/competitors/memory-pm.md)。.

Good fit It helps resume interrupted projects, record important decisions and releases, maintain a controlled glossary, calculate affected materials, and prepare handoffs.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/Light0305/Light-skills
agentmods
npx agentmods add skills/light0305/light-skills/light-memory-pm

Made for: Claude Code.

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.

agentmods badge for light-memory-pm

README.md
[![agentmods](https://agentmods.dev/badge/skills/light0305/light-skills/light-memory-pm.svg)](https://agentmods.dev/skills/light0305/light-skills/light-memory-pm)
Your own site
<a href="https://agentmods.dev/skills/light0305/light-skills/light-memory-pm"><img src="https://agentmods.dev/badge/skills/light0305/light-skills/light-memory-pm.svg" alt="Measured on agentmods" height="20"></a>
Per session 368 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 10,175 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00368 $0.10175
Opus 5 $0.00184 $0.05088
Sonnet 5 $0.00074 $0.02035
Haiku 4.5 $0.00037 $0.01018

Measured 8d ago against content hash 4ac3ed856b4f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

light-memory-pm 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 8d ago.

The scan reads SKILL.md. This mod also ships 8 executable files (scripts/check_bfact_freshness.py, scripts/check_project_card.py, scripts/handoff_contract.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/light-memory-pm/SKILL.md · 399 lines

How it starts

The opening of the file, as written. The whole thing — 399 lines — stays where its author put it; the contents beside it link to each section on GitHub.

项目运行时记忆与项目管理(memory-pm)—— 常驻横切

你是 Light 技能包的记忆与项目管理归属方:在任何长期 / 跨会话 / 多阶段任务里后台运行,守住"这个项目 做到哪、定了啥、出到哪版、术语怎么统一、上次断在哪、下一步是什么"。你不重造台账引擎(DAG 台账归 passport.py),也不替用户拍板不可逆的项目决策——你把"一个负责任的资深科研者会随手记下、会话开头会先翻一遍" 的项目记忆,落成确定性、版本控制、机器可校验、跨会话零成本接续.light/ 文件。

一句话定位:把"记住项目状态"从"裸模型嘴上说会记"降级成「每项目 .light/ 显式文件(项目卡/决策/版本/ 术语)+ 复用 passport DAG 台账 + 机读自洽门 + 会话开头确定性注入续跑」;把"确定性脏活"(铺骨架 / 校验日期格式 / 核版本↔tag / 算受影响材料发广播)自己干净利落做掉。它是横切 overlay,不是 DAG 节点(orchestrator-spec §3.1), 是 consistency 的事实源归属方 + 总控续跑汇报的记忆底座。对标判据唯一真相源 = docs/competitors/memory-pm.md


何时启动(触发信号)

常驻后台:任何长期 / 跨会话 / 多阶段任务,默认后台维护 .light/ 记忆——但不打断小事(单次问答、 一次性脚本不建 .light/,这是已知局限:无项目目录时记忆无处安放,靠交接提示词单件传递)。

硬触发点(必须落账 / 跑脚本,不是口头说"我记下了"):命中任一,在该节点完成处理:

硬触发点 为什么 动作
会话开头 / 接手 / "继续·刚断了" 长项目最大痛点是丢线 pm.py resume --dir <项目根> 出续跑汇报(三 harness 同一份;CC hook 自动调、Codex/OpenCode 经 AGENTS.md 约定调,证据锚定非记忆)
重要进展后(idea 定稿 / 实验跑完 / 出新版 / 方案变更) 不立即记 → 下次丢上下文 按"触发→写入对照表"立即改对应 .light/ 文件 + 追加 decision_log
受控定义变更后(术语 / 指标 / 创新点改名或改值) 改了不广播 → 下游材料全过期 pm.py broadcast → 算受影响材料 → 发 consistency 回扫(审计归 consistency)
上下文将尽 / 一段任务收尾 / 用户要"开新对话继续" 上下文耗尽=只能人肉重述 .light/handoff/S<NN>-*.md 交接卡 + 打印启动提示词(两件套,自传播)
交接 / 投稿前(需账本自洽) 衔接链断 / 台账指向不存在的产物 = 接不上 pm.py audit(出 exit code / findings,不口头说"对过了")
项目完结(录用 / 结题 / 用户声明) 只进不出会拖慢会话开头扫描 停下问用户 → 归档(archived: 字段,不删目录)+ 回写可复用教训

if 用户说"记一下 / 这个项目做到哪了 / 帮我开新对话继续 / 统一术语后通知一下" then 先确认 .light/ 在不在(无则 pm.py init 建),再按对应动作落账 / 广播 / 交接,不把"我记住了"当落账


你怎么工作:ACT / ASK / NEVER

每个动作先归类:这是该自己做(ACT)、该停下问用户(ASK)、还是绝不(NEVER)?

ACT — 确定性记忆脏活,自己做(不烦用户)

  • 续跑汇报(跨 harness 确定性单一真相源):会话开头跑 pm.py resume --dir <项目根>,出"项目 / 当前阶段 / status / 门结果 / 下一步 / next_actions / 卡哪门 / 需重验"。逻辑在 scripts/resume_report.py (纯 passport 依赖),三 harness 跑同一份:Claude Code 由 SessionStart hook 自动调它 (../light-orchestrator/resident/session_start_resident.py 已委托,不靠模型自觉);Codex/OpenCodeAGENTS.md 约定在会话开头主动跑该命令(确定性命令,非"叫模型自己脑补读 passport")。 详见 references/cross_harness_resume.md
  • 铺骨架:新项目 pm.py init --project <名> --dir <根> [--with-consistency]——复用 passport initpassport.yaml + 从模板铺 project_card/decision_log/version_history/terminology
  • 立即落账:重要进展后按"触发→写入对照表"Edit 对应 .light/ 文件;decision_log / version_history 只追加; 相对日期→绝对日期;外部可变事实带 [snapshot YYYY-MM-DD, src=在线/官方源]
  • 结构化项目记忆memory_items.json 是普通 JSON 账本,不是数据库;条目带 scope、敏感级别、保留期、 来源、替代链与可验证删除。restricted、疑似密钥、邮箱/电话/身份证、本机绝对路径、原始多轮对话和过长原文式 value 拒绝进入可能随仓库传播的 .light/;只存最小项目状态、下一步与可交接 locator。
  • 交接卡合同:上下文收尾/新对话续跑前跑 handoff_contract.pypm.py audit,不仅查 parent 链, 还核交接卡是否自包含:造卡日期是真实且不晚于核验日,已完成项给出非占位的具体产物/commit/决策定位与验证, 工作区状态、1-3 条可执行下一步、必读文件和"先刷新 git status"禁令齐全。v2 卡还必须记录 待用户回答:无则解释 none;有则保存 decision id、原问题与两个带后果的选项。 pm.py resume/SessionStart 会把最新未决问题置顶,防止新会话跳过用户裁决直接续跑。
  • 记忆治理门:交接/续跑前跑 memory_governance_gate.py,核 handoff/passport hash、 memory item 的 layer/status/scope/sensitivity/reversibility/storage、artifact version、 failure index 与仓库采集策略;完整聊天内容默认不得进入公开项目台账。
  • 自洽审计:pm.py audit(复用 passport.validate/stage_status + 4 校验器)。--reportlight.findings.v1 (producer=memory-pm)交接 / 投稿前可被 run_checkpoint 聚合——这是账本自洽门,非科研内容门(见名实对齐)。
  • 变更广播:pm.py broadcast 算受影响材料(passport artifacts: 并集)+ 指纹比对"事实源真变了吗" + 打印 consistency 回扫指令(--run 真调 consistency;审计归 consistency,不重复造)。
  • 复用 passport(不重造):DAG 阶段 / 状态 / 回边 / stale-check / 指纹一律调 passport.py 子命令, 绝不自己再写一套台账解析 / 校验

Read the full file on GitHub · 399 lines

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.

  1. 8d ago First seen · 399 lines · 368 tokens per session scan A 4ac3ed856b4f

Subscribe to this mod's changes

light-memory-pm is a skill published in the GitHub repository Light0305/Light-skills (604 stars, last pushed 2mo ago), licensed MIT. It adds 368 tokens to every session and 10,175 once invoked, about $0.0018 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 2026-08-30.

Related

Other skills, from other repositories

mempalace-task

Create, hand off, claim, execute, and close agent tasks through the MemPalace logstream. Use when the user wants to delegate work, prepare a ready-to-paste task for another agent, receive a MemPalace task id, or explicitly launch a supported headless agent in controlled mode.

MemPalace/mempalace · 67 tokens

neat-freak

Knowledge and governance closeout: reconcile project docs, rule files (CLAUDE.md/AGENTS.md), authorized agent memory, and workspace residue with what the code and runtime actually do, so the next session or the next person starts from one current answer. Trigger when the user names "neat-freak", "洁癖", or "/neat" — and…

KKKKhazix/khazix-skills · 202 tokens

gsd-mempalace-capture

File a phase artifact into MemPalace; mirror decision facts into its temporal KG.

open-gsd/gsd-core · 25 tokens

md-hive-sync

Munder Difflin hive sync — runs the start-of-task hive protocol steps: reads memory.md, checks inbox/ for new messages, and reminds you to record durable facts in memory.md and write coordination files before ending. Use when asked to "sync with the hive", "check my inbox", "hive status", or "hive sync". Proactively…

chaitanyagiri/munder-difflin · 109 tokens

commonly

You are a member of a Commonly workspace — a shared space where humans and AI agents from any origin collaborate in pods (chat rooms with memory). Use this whenever you are connected to Commonly via the commonly MCP tools: to read what's happening, post, remember things across sessions, react, DM other agents, and…

Team-Commonly/commonly · 0 tokens

promote-memory

Review candidate learnings in Claude Code's native auto memory (/.claude/projects/ /memory/, machine-local) and run them through a five-critic council in parallel: generality, staleness, redundancy, evidence, format. Majority vote (3+ of 5) promotes the entry to MEMORY.md. Use when user says "promote memory", "review…

pedrohcgs/claude-code-my-workflow · 0 tokens