Agent skill

Memory Consolidation

by modimihir07 in modimihir07/agentic-os

Weekly synthesis of accumulated notes and memory optimization

MITAuto-check passed

Install Memory Consolidation

skills CLI
$ npx skills add modimihir07/agentic-os --skill memory-consolidation -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install modimihir07/agentic-os memory-consolidation --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/modimihir07/agentic-os.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/memory-consolidation .claude/skills/memory-consolidation && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
memory-consolidation
GitHub stars
193
Token cost
~243 tokens
SKILL.md length
98 words
Files
4
Skills in repo
12
Repo updated
First seen
Licence
MIT

At a glance

Weekly synthesis of accumulated notes and memory optimization

  • Works in 6 steps: Read all learnings.md files across skills → Read recent-decisions.md and archive… → Compress duplicated lessons into single… → …
  • SKILL.md covers Description, When to Use, Process and Output, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Memory Consolidation is an agent skill from modimihir07/agentic-os. Weekly synthesis of accumulated notes and memory optimization

Its SKILL.md is about 240 tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files (for example `eval.json`, `learnings.md` and `score-history.json`).

The repository describes itself as: Agentic OS: Multi-agent orchestration platform for opencode, Hermes & Gemini CLI. Skills hub, scheduler, cost analytics, memory & backup. The licence is MIT.

Example prompts

  • “/memory-consolidation”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Read all learnings.md files across skills
  2. Read recent-decisions.md and archive entries older than 30 days
  3. Compress duplicated lessons into single entries
  4. Update memory.md with synthesized insights
  5. Prune eval score-history.json to last 20 entries
  6. Flag any contradictions in learnings for user review

What it can do on your machine

Read from SKILL.md and the folder at commit c7ebbb4. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Memory Consolidation loads about 243 tokens when it runs. Until then it costs about 21 tokens; SKILL.md has 98 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~21
When it runs · the whole SKILL.md, loaded when a task matches
~243

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from modimihir07/agentic-os at commit c7ebbb4, republished under its MIT licence (© modimihir07). 98 words, ~243 tokens.

Download SKILL.mdSave it as .claude/skills/memory-consolidation/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
memory-consolidation
description
Weekly synthesis of accumulated notes and memory optimization
version
1.0.0
author
Agentic OS
tags
memory, consolidation, cleanup, maintenance

Memory Consolidation

Description

Synthesizes and compresses accumulated memory files. Removes redundant information, updates summaries, and archives outdated content.

When to Use

  • Weekly (scheduled)
  • When learnings.md exceeds 600 words
  • When recent-decisions.md has 30+ entries

Process

  1. Read all learnings.md files across skills
  2. Read recent-decisions.md and archive entries older than 30 days
  3. Compress duplicated lessons into single entries
  4. Update memory.md with synthesized insights
  5. Prune eval score-history.json to last 20 entries
  6. Flag any contradictions in learnings for user review

Output

Consolidated memory with archived sections, updated summaries, and pruning report

Agent Assignment

  • Primary: hermes
  • Fallback: opencode

© modimihir07, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files in skills/memory-consolidation of modimihir07/agentic-os.

  • SKILL.md
  • eval.json
  • learnings.md
  • score-history.json

Open the folder on GitHubat commit c7ebbb4

Compare with similar skills

Memory Consolidation next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Memory Consolidation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Memory Consolidation this skillmodimihir07/agentic-os193—~243Automated safety check: PassMIT
Weekly Synthesisheyitsnoah/claudesidian2.6k—~530Automated safety check: PassMIT
Weekly Project Digeststhedotmack/claude-mem99k—~3.5kAutomated safety check: PassApache-2.0
Weekly Review PlanningNousResearch/hermes-agent252k—~994Automated safety check: PassMIT
Weekly Reviewcursor/plugins10k1 repos~226Automated safety check: PassNone
Weekly Reviewalirezarezvani/claude-skills28k—~1.4kAutomated safety check: PassMIT

Similar skills

  • Weekly Synthesis

    heyitsnoah/claudesidian

    Create a comprehensive synthesis of the week's work and thinking.

    2.6k GitHub stars~530 tokensUpdated 6 mo ago
    Knowledge ManagementAuto-check passed
  • Weekly Project Digests

    thedotmack/claude-mem

    Turns a project's claude-mem timeline into a week-by-week narrative, splitting it by ISO week and running one subagent per week that receives the prior week's carry-forward block.

    99k GitHub stars~3.5k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Weekly Review Planning

    NousResearch/hermes-agent

    Weekly reset: commitments, stalled work, next-week plan. An agent skill from NousResearch/hermes-agent.

    252k GitHub stars~994 tokensUpdated today
    Knowledge ManagementAuto-check passed
  • Weekly Review

    cursor/plugins

    Official

    Produce a weekly synthesis of authored commits with highlights by bugfix, tech debt, and net-new work

    10k GitHub starsUsed in 1 repo~226 tokens
    Knowledge ManagementAuto-check passed
  • Weekly Review

    alirezarezvani/claude-skills

    A skill your agent uses when someone wants to run a weekly review, close open loops, audit stalled projects and commitments, get their system back to trusted, restart a lapsed review habit, or says…

    28k GitHub stars~1.4k tokensUpdated 1 mo ago
    Knowledge ManagementAuto-check passed
  • HTML Ppt Weekly Report

    nexu-io/open-design

    OpenDesign's weekly growth review: stars, installs, activation — the number, the driver, and the recommended move.

    100k GitHub stars~1.3k tokensUpdated today
    Documents & OfficeAuto-check passed

More from modimihir07/agentic-os

All 12 skills in this repo
  • Code Review

    modimihir07/agentic-os

    Automated code review with checklist and quality gates. An agent skill from modimihir07/agentic-os.

    193 GitHub stars~222 tokensUpdated 1 mo ago
    Auto-check passed
  • Cost Analytics

    modimihir07/agentic-os

    Tracks token usage and API costs across all providers. An agent skill from modimihir07/agentic-os.

    193 GitHub stars~225 tokensUpdated 1 mo ago
    Auto-check passed
  • Daily Standup

    modimihir07/agentic-os

    Morning briefing with project status overview. An agent skill from modimihir07/agentic-os.

    193 GitHub stars~203 tokensUpdated 1 mo ago
    Auto-check passed
  • Devops Audit

    modimihir07/agentic-os

    GCP/K8s infrastructure audit and health check. An agent skill from modimihir07/agentic-os.

    193 GitHub stars~214 tokensUpdated 1 mo ago
    Auto-check passed
  • Goal Planner

    modimihir07/agentic-os

    Refines user inputs into executable step-by-step plans. An agent skill from modimihir07/agentic-os.

    193 GitHub stars~216 tokensUpdated 1 mo ago
    Auto-check passed
  • Heartbeat

    modimihir07/agentic-os

    Lightweight system health monitoring skill. An agent skill from modimihir07/agentic-os.

    193 GitHub stars~217 tokensUpdated 1 mo ago
    Auto-check passed

Questions about Memory Consolidation

What does Memory Consolidation do?

Weekly synthesis of accumulated notes and memory optimization. Memory Consolidation is an agent skill from modimihir07/agentic-os.

How do I install Memory Consolidation in Claude Code?

Run `npx skills add modimihir07/agentic-os --skill memory-consolidation -a claude-code`. Or copy the skill folder (skills/memory-consolidation in modimihir07/agentic-os) into .claude/skills/memory-consolidation in your project. Claude Code loads it when a task matches its description.

How do I install Memory Consolidation in Codex?

Run `npx skills add modimihir07/agentic-os --skill memory-consolidation -a codex`. Or copy the skill folder (skills/memory-consolidation in modimihir07/agentic-os) into .agents/skills/memory-consolidation in your project. Codex loads it when a task matches its description.

Can I use Memory Consolidation in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add modimihir07/agentic-os --skill memory-consolidation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/memory-consolidation, .gemini/skills/memory-consolidation, .github/skills/memory-consolidation and .opencode/skills/memory-consolidation in your project.

What does Memory Consolidation need to run?

SKILL.md names no scripts, command-line tools or credentials: Memory Consolidation is instructions for the agent only.

Does Memory Consolidation access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Memory Consolidation safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Memory Consolidation use?

Memory Consolidation is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Memory Consolidation use?

About 243 tokens (SKILL.md is roughly 972 characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Memory Consolidation?

Skills that share tags, products or a category with Memory Consolidation: Weekly Synthesis (heyitsnoah/claudesidian, 2.6k stars), Weekly Project Digests (thedotmack/claude-mem, 99k stars), Weekly Review Planning (NousResearch/hermes-agent, 252k stars) and Weekly Review (cursor/plugins, 10k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Memory Consolidation?

modimihir07 (a GitHub user) maintains it in modimihir07/agentic-os, which has 193 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on August 11, 2026.

Source: modimihir07/agentic-os on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.