memory-continuity

A system for carrying selected project context from one coding session to the next. It stores current memory, an index, and dated snapshots in a fixed folder structure.

In plain words
What is it for?
Use it to create and maintain continuity files under .agentic/memories/, including the current memory file, an index, and timestamped handoffs.
Why use it?
It reduces the need to reconstruct important decisions and context after starting a clean session.

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/soulcodex/agentic/memory-continuity
Any agent
npx skills add soulcodex/agentic --skill memory-continuity
Clone the repo
git clone --depth 1 https://github.com/soulcodex/agentic

Made for: Claude Code, Codex.

Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 967 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 $0.00030 $0.00967
Opus 5 $0.00015 $0.00483
Sonnet 5 $0.00006 $0.00193
Haiku 4.5 $0.00003 $0.00097

Measured 2d ago against content hash 860def6a9a68, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memory-continuity 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.

skills/agentic/memory-continuity/SKILL.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memory Continuity Skill

Use this skill to preserve high-value context between clean sessions while avoiding noisy or low-signal carryover.

Storage Layout (Hybrid Contract)

Use this deterministic structure:

.agentic/
  memories/
    MEMORY.md
    index.md
    snapshots/
      YYYY-MM-DDTHH-MM-SSZ.md

Rules:

  • If .agentic/memories/ does not exist, create it and required child paths.
  • MEMORY.md is the current canonical continuity file.
  • index.md is a small pointer log to snapshots.
  • snapshots/ stores timestamped continuity checkpoints.
  • Use memory-current-template.md for MEMORY.md initialization.
  • Use index-template.md for index.md initialization.

First-Run Initialization and Bootstrap Rules

When MEMORY.md and index.md do not exist:

  1. If there is active iteration context (for example an open issue/PR, active branch work, or already-decided next steps), initialize both files from templates immediately.
  2. If there is no active iteration context, inspect commit history for signal:
  • if history is rich enough to derive meaningful continuity, ask the user before generating a brief bootstrap memory from commits;
  • if history is not rich enough, ask the user before leaving memory uninitialized.
  1. Never invent synthetic history. If signal is insufficient, state that explicitly.

Start-of-Session Retrieval Workflow

  1. If files are missing, apply First-Run Initialization and Bootstrap Rules.
  2. Read .agentic/memories/MEMORY.md if present.
  3. If index.md exists, read only the latest 1 to 3 snapshot pointers.
  4. Extract only high-signal items:
  • current objective
  • decisions made and rationale
  • open risks/questions
  • next concrete steps
  1. Do not import verbose logs, full transcripts, or resolved low-impact details.

End-of-Session Update Workflow

  1. Create directories/files if missing:
  • .agentic/memories/
  • .agentic/memories/snapshots/
  • .agentic/memories/MEMORY.md (from memory-current-template.md)
  • .agentic/memories/index.md (from index-template.md)
  1. Build a new memory entry using memory-template.md.
  2. Update MEMORY.md additively:
  • keep existing unresolved items
  • append new high-signal updates
  • remove or compress resolved/noisy items
  1. Write a timestamped snapshot:
  • filename format: YYYY-MM-DDTHH-MM-SSZ.md
  1. Append one row in index.md pointing to the snapshot and objective.

Read the full file on GitHub · 124 lines

Files

What ships with it

3 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. 2d ago First seen · 124 lines · 30 tokens per session scan A 860def6a9a68

Subscribe to this mod's changes

memory-continuity is a skill published in the GitHub repository soulcodex/agentic (10 stars, last pushed 2d ago), licensed MIT. It adds 30 tokens to every session and 967 once invoked, about $0.0002 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

research-repository

Build a repository that makes findings findable, reusable, and cumulative across teams. Use when the same research keeps getting redone. For synthesising one study, use affinity-diagram.

Owl-Listener/designer-skills · 43 tokens

survey-design

Design unbiased survey instruments — question wording, scales, and sampling — to measure attitudes at scale. Use when you need quantitative breadth. For behavioural experiments, use a-b-test-design (prototyping-testing).

Owl-Listener/designer-skills · 47 tokens

localization-design

Design for multiple languages, writing directions, and cultural contexts — text expansion, RTL mirroring, and locale formats. Use when shipping beyond one locale. For the words themselves, use ux-writing (designer-toolkit).

Owl-Listener/designer-skills · 49 tokens

design-negotiation

Advocate for design quality, scope, and timeline with partners and leadership using evidence and shared goals. Use in the conversation itself. For the commercial vocabulary behind it, use business-design (ux-strategy).

Owl-Listener/designer-skills · 48 tokens

design-debt-audit

Inventory and prioritise accumulated design inconsistencies across a product. Use when drift has built up over time. For token coverage specifically use design-token-audit (designer-toolkit); for WCAG gaps use accessibility-audit (design-systems).

Owl-Listener/designer-skills · 59 tokens

design-impact-reporting

Communicate design's contribution to business and user outcomes in stakeholder language. Use when reporting results upward. For choosing the metrics in the first place, use metrics-definition (ux-strategy).

Owl-Listener/designer-skills · 44 tokens