agentmods.dev

memory-management

memory-management is a skill for Claude Code, Codex from richfrem/agent-plugins-skills. It costs 27 tokens per session (487 once invoked), scanned A, original, MIT.

A filesystem-based memory system for preserving useful project knowledge across agent sessions. It stores procedural instructions, durable Markdown notes, confidence labels, and records of past outcomes.

In plain words
What is it for?
It is for organizing project playbooks, edge cases, decisions, failure logs, and other knowledge used during future tasks.
Why use it?
It helps an agent retain context between sessions without relying on an external vector database or background service.

Skill for Claude CodeCodex

Part of the agent-memory plugin — 13 skills, 2 commands, 9 agents shipped together

not rated 6 yesterday A scan 27 tokens original MIT
View the source file richfrem/agent-plugins-skills
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 skills/richfrem/agent-plugins-skills/memory-management
Any agent
npx skills add richfrem/agent-plugins-skills --skill memory-management
Clone the repo
git clone --depth 1 https://github.com/richfrem/agent-plugins-skills

Made for: Claude Code, Codex.

Or install agent-memory, the plugin that ships this one along with the rest of its 13 skills, 2 commands, 9 agents.

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 memory-management

README.md
[![agentmods](https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/memory-management.svg)](https://agentmods.dev/skills/richfrem/agent-plugins-skills/memory-management)
Your own site
<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/memory-management"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/memory-management.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 487 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.

ModelPer sessionOnce invoked
Fable 5 $0.00027 $0.00487
Opus 5 $0.00014 $0.00244
Sonnet 5 $0.00005 $0.00097
Haiku 4.5 $0.00003 $0.00049

Measured yesterday against content hash a77455119870, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memory-management 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 yesterday.

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.

plugins/agent-memory/skills/memory-management/SKILL.md · 37 lines

What it actually says

Memory Management (3-Layer Filesystem Engine)

Zero-dependency memory system providing high-speed cognitive continuity across agent sessions without external vector databases or daemon processes.

The 3 Filesystem Layers

  1. Layer 1: Runtime Context (Lean Procedural Core)

    • Lean SKILL.md files (target <= 100 lines).
    • Loaded strictly on-demand.
    • Inference Restriction: Historical raw execution traces and multi-page wiki dossiers are barred during active task execution to eliminate context window bloat.

  2. Layer 2: Compounding Wiki Layer (Permanent Knowledge)

    • Permanent Markdown documents stored in wiki/ and plugin references/.
    • Contains: domain playbooks, known edge cases, negative constraints, map-debt.md, and evolution-log.md.
    • Knowledge Status Taxonomy: Entries are tagged with explicit confidence (OBSERVED, HYPOTHESIS, CONFIRMED, REJECTED, OPEN).
    • Confidence Decay: Knowledge not re-verified within 30 days decays from CONFIRMED to OBSERVED.
    • Asymmetric Persistence Rule: When an evolution attempt fails, code mutations are rolled back, but wiki insights, edge-case discoveries, and failure logs are NEVER rolled back.

  3. Layer 3: Safe Audit Layer (Append-Only Manifests)

    • Stored in .agent/learning/traces/cycle_manifests.jsonl.
    • Tracked audit log capturing event sequences, hashes, exit codes, and affected paths (zero raw terminal text or credentials).
    • Audited exclusively via verify_evolution_receipt.py.

Standardized Retrieval Protocol

All memory lookups use native filesystem tools:

  1. Targeted Exact Match: rg "<symbol-or-pattern>" <dir> or grep_search.
  2. Playbook Inspection: Direct file read of references/<topic>-playbook.md or wiki/<topic>.md.
  3. Map Debt Audit: Scan references/map-debt.md for existing open friction items before starting tasks.
Files

What ships with it

14 files 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.

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. yesterday First seen · 37 lines · 27 tokens per session scan A a77455119870

Subscribe to this mod's changes

memory-management is a skill published in the GitHub repository richfrem/agent-plugins-skills (6 stars, last pushed yesterday), licensed MIT. It adds 27 tokens to every session and 487 once invoked, about $0.0001 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 2026-09-03.

Memory and contextagent-skillsagentic-frameworkagentic-harnessagentic-osclaude-code-skillclaude-plugins
Related

Other skills, from other repositories

agent-collective-intelligence-coordinator

Agent skill for collective-intelligence-coordinator - invoke with $agent-collective-intelligence-coordinator.

ruvnet/ruflo · 29 tokens

wiki-fold

Create a bounded, extractive, structurally idempotent rollup of recent Obsidian wiki log entries, with dry-run preview by default and one optional transaction apply. Use for manual log compression without modifying child pages. Triggers: fold the log, run a fold, run wiki-fold, log rollup, roll up log entries, commit…

AgriciDaniel/claude-obsidian · 76 tokens

kapso-whatsapp

How to interact with Kapso WhatsApp from the swarm — read inbound webhook payloads (text AND media), fetch message history, send free-form messages within the 24h session window (and template messages outside it), mark-as-read, show the typing indicator, send reactions, download media, verify webhook signatures, and…

desplega-ai/agent-swarm · 156 tokens

scheduled-task-resilience

Guardrails for polling, scheduled jobs, and long-running external operations. Use whenever a task waits on CI, builds, deploys, browser jobs, or another asynchronous API so work survives heartbeat checks without duplicate delivery.

desplega-ai/agent-swarm · 48 tokens

user-management

How to manage the user registry — creating users for new Slack/GitHub/GitLab/Linear identities, managing aliases, resolving users across platforms. Use when a new human interacts with the swarm or when user identity needs updating.

desplega-ai/agent-swarm · 49 tokens

todos

Handle the agent personal todos.md file.

desplega-ai/agent-swarm · 9 tokens