What is 003-plan-memory?

An agent for shared memory at the plan level, where several coding agents can record discoveries, decisions, lessons, and open questions. A plan is a coordinated piece of work, and the shared notes are stored in a plan.memory.md file.

Use it to view or update plan memory, record shared discoveries and decisions, add lessons or questions, and promote a finding from one agent's notes into the shared plan notes.

It keeps useful findings available to all agents working on the same plan instead of leaving them in one agent's session. It also records which agents contributed information.

003-plan-memory — Agent by paulbreuler

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.

agentmods

npx agentmods add agents/paulbreuler/limps/003-plan-memory

Clone the repo

git clone --depth 1 https://github.com/paulbreuler/limps

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 416 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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	$0.00000	$0.00416
Opus 5	$0.00000	$0.00208
Sonnet 5	$0.00000	$0.00083
Haiku 4.5	$0.00000	$0.00042

Measured 2d ago against content hash 81f4866f1bcd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

003-plan-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 2d 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.

plans/0047-limps-context-hierarchy/agents/003-plan-memory.md · 56 lines

What it actually says

Agent 003: Plan Memory System

Objective

Implement plan-level shared memory for cross-agent learnings.

Tasks

Plan memory manager (src/memory/plan-memory.ts)
- getPlanMemory(planId): Load plan.memory.md
- addSharedDiscovery(planId, text, contributorAgents)
- addPlanDecision(planId, choice, affectedAgents, rationale)
- addLesson(planId, text)
- addOpenQuestion(planId, text)
Promotion from agent to plan
- promoteToShared(planId, agentId, type, index)
- Copy finding/decision to plan memory
- Track which agent contributed
Plan memory CLI
- limps memory plan show <plan> — Display plan memory
- limps memory plan add <plan> discovery <text>
- limps memory plan add <plan> decision <choice> --affects <agents>
- limps memory promote <plan> <agent> finding-3 — Promote from agent

Plan Memory File

plans/0042-knowledge-graph/
├── 0042-plan.md
├── plan.memory.md          # Shared memory
└── agents/
    ├── 001.md
    └── 001.memory.md       # Agent memory

Acceptance Criteria

Plan memory stored in plan.memory.md
Shared discoveries track contributing agents
limps memory promote moves agent findings to plan
Plan memory included in context resolution for all agents
Open questions visible to all agents in plan

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.

2d ago First seen · 56 lines · 0 tokens per session scan A 81f4866f1bcd

Subscribe to this mod's changes

003-plan-memory is an agent published in the GitHub repository paulbreuler/limps (10 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 416 tokens. 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.

Building agents LLM Memory and context ai-agents ai-planning ai-testing-best-practices mcp mcp-server plan shared

context-manager

Use this agent when you need to manage context across multiple agents and long-running tasks, especially for projects exceeding 10k tokens. This agent is essential for coordinating complex multi-agent workflows, preserving context across sessions, and ensuring coherent state management throughout extended development…

czlonkowski/n8n-mcp · 0 tokens

chainaware-rug-pull-detector

Specialized Web3 rug pull detection agent powered by ChainAware's Behavioral Prediction MCP. Use this agent PROACTIVELY whenever a user wants to check if a smart contract, liquidity pool, DeFi token, or new project is safe to invest in or deposit funds into. Automatically invoke when the user provides a contract…

ChainAware/behavioral-prediction-mcp · 177 tokens

003-plan-memory