agentic-memory

agentic-memory is a skill for Claude Code, Codex from RajanChavada/Rosetta. It costs 20 tokens per session (3,472 once invoked), scanned A, original, MIT.

A project-memory system for AI agents that stores long-term architectural rules, team knowledge, and important decisions.

In plain words
What is it for?
Preserving project knowledge, organising it into memory levels, and prompting the user before archiving undocumented team conventions or decisions.
Why use it?
It helps prevent useful context, undocumented workarounds, and reasons behind project choices from being lost between tasks.

Skill for Claude CodeCodex

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/rajanchavada/rosetta/agentic-memory
Any agent
npx skills add RajanChavada/Rosetta --skill agentic-memory
Clone the repo
git clone --depth 1 https://github.com/RajanChavada/Rosetta

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.

agentmods badge for agentic-memory

README.md
[![agentmods](https://agentmods.dev/badge/skills/rajanchavada/rosetta/agentic-memory.svg)](https://agentmods.dev/skills/rajanchavada/rosetta/agentic-memory)
Your own site
<a href="https://agentmods.dev/skills/rajanchavada/rosetta/agentic-memory"><img src="https://agentmods.dev/badge/skills/rajanchavada/rosetta/agentic-memory.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,472 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 $0.00020 $0.03472
Opus 5 $0.00010 $0.01736
Sonnet 5 $0.00004 $0.00694
Haiku 4.5 $0.00002 $0.00347

Measured 3d ago against content hash ba83aa4ec6c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentic-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 3d 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.

.windsurf/skills/agentic-memory/SKILL.md · 580 lines

How it starts

The opening of the file, as written. The whole thing — 580 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agentic Memory Skill

Overview

This skill provides a sophisticated memory management system that preserves tribal knowledge, maintains a clear memory hierarchy, and ensures important context never disappears. It implements THE MEMORY CONTRACT - explicit rules that all agents must follow.


THE MEMORY CONTRACT - AGENT BEHAVIOR RULES

Rule 1: Tribal Knowledge Preservation (CRITICAL)

NEVER let important learnings disappear.

When you encounter tribal knowledge (implicit rules, undocumented patterns, workarounds, "why we do X this way"):

  1. PROMPT THE USER with clear reasoning:

    This seems like tribal knowledge: [description].
    Archive to .ai/archive/tribal-knowledge.md?
    
  2. AWAIT APPROVAL before archiving

  3. Archive is APPEND-ONLY - never modify existing entries

Tribal knowledge indicators:

  • "We always do it this way" (no documented reason)
  • Undocumented workarounds for known issues
  • Implicit architectural decisions
  • Team conventions not in code or docs
  • "Don't touch X without Y" warnings
  • Historical context from old issues/PRs

Rule 2: Memory Hierarchy (STRICT ORDER)

The memory system has 5 levels. Always read and update in this order:

  1. PROJECT_MEMORY.md - Architectural decisions, domain rules, "Why"

    • Location: .ai/memory/PROJECT_MEMORY.md
    • Content: Long-lived architectural truths
    • Updates: Propose to user before modifying
  2. AUTO_MEMORY.md - Heuristics, patterns, gotchas, shortcuts

    • Location: .ai/memory/AUTO_MEMORY.md
    • Content: Agent-maintained learnings and patterns
    • Updates: Append freely, promote to PROJECT_MEMORY.md when appropriate
  3. logs/daily/YYYY-MM-DD.md - Session activity, what was attempted

    • Location: .ai/logs/daily/YYYY-MM-DD.md
    • Content: Daily session logs with outcomes
    • Updates: Auto-log for significant work
  4. archive/tribal-knowledge.md - Append-only tribal wisdom

    • Location: .ai/archive/tribal-knowledge.md
    • Content: Undocumented patterns and historical context
    • Updates: User approval required, append-only

Read the full file on GitHub · 580 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. 3d ago First seen · 580 lines · 20 tokens per session scan A ba83aa4ec6c3

Subscribe to this mod's changes

agentic-memory is a skill published in the GitHub repository RajanChavada/Rosetta (3 stars, last pushed 3mo ago), licensed MIT. It adds 20 tokens to every session and 3,472 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 2026-08-31.

Related

Other skills, from other repositories

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

auditing-subgroup-fairness

Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…

maziyarpanahi/openmed · 148 tokens

agent-memory

../../../engineering/agent-memory/skills/agent-memory/SKILL.md.

alirezarezvani/claude-skills · 0 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens