vbcherepanov/total-agent-memory/codex-skill

Claude Code and agent skill by vbcherepanov/total-agent-memory

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Activate this skill when starting a new session, beginning a new task, saving knowledge, recalling past decisions, or after completing significant work. Also activate on errors to log them for pattern analysis. Relevant when the user asks about memory, past context, lessons learned, decisions history, project conventions, or self-improvement.

Install

npx vskill@latest install vbcherepanov/total-agent-memory/codex-skill

SKILL.md

Persistent Memory System

You have access to a persistent cross-session memory via MCP tools. Knowledge survives between sessions and is shared across agents working on the same project.

Session Start

Always run these two calls before any work:

self_rules_context(project="<project>")
memory_recall(query="<current task description>", project="<project>")

If relevant knowledge is found, mention it briefly and apply it.

Auto-Save Rules

Save knowledge automatically -- never ask the user whether to save.

EventtypeWhat to save
Architectural decisiondecisionDecision + WHY + rejected alternatives
Non-trivial bug fixsolutionSymptom -> root cause -> fix
Gotcha or pitfall discoveredlessonExpected vs actual + takeaway
Infrastructure or config setupfactConfig details + key parameters
Project pattern establishedconventionRule + code example
Session endingfactSummary of what was done + what remains

Format:

memory_save(
content="Concise, actionable description",
type="decision|solution|lesson|fact|convention",
project="<project>",
tags=["relevant", "tags"],
context="Why this matters. For decisions: always explain WHY."
)

Do NOT save: trivial edits, intermediate steps, information obvious from the code.

Error Logging

On any error (command failure, wrong assumption, API error, timeout), log it automatically:

self_error_log(
description="What went wrong",
category="code_error|logic_error|config_error|api_error|timeout|loop_detected|wrong_assumption|missing_context",
severity="low|medium|high|critical",
fix="How it was fixed (empty if unresolved)",
project="<project>"
)

When pattern_detected: true is returned (3+ similar errors), extract an insight:

self_insight(action="add", content="Generalized lesson", category="<error_category>", source_error_ids=[...])
Self-Improvement Pipeline

Errors -> Insights -> Rules (SOUL).

  • Insights with importance >= 5 and confidence >= 0.8 can be promoted to rules
  • Rules are loaded at session start via self_rules_context
  • Rate rules after task completion: self_rules(action="rate", id=N, success=true/false)
  • At session end, reflect: self_reflect(reflection="...", task_summary="...", outcome="success|partial|failure")
Privacy

The server auto-redacts API keys, JWTs, passwords, emails, and credit cards before storage. Use <private>...</private> tags to explicitly exclude sensitive content:

memory_save(content="Connected to <private>prod-host:5432</private>", type="fact", project="<project>")
Quick Reference (32 tools)

Core Memory (12):

ToolPurpose
memory_recallSearch past knowledge (4-tier: keyword, semantic, fuzzy, graph)
memory_saveStore new knowledge with type, project, tags
memory_updateSupersede existing knowledge with a new version
memory_timelineBrowse session history
memory_statsHealth metrics and storage info
memory_consolidateFind and merge duplicate records
memory_exportExport all knowledge as JSON
memory_forgetApply retention policy
memory_historyView version chain for a record
memory_deleteSoft-delete a record
memory_relateCreate typed relations between records
memory_search_by_tagBrowse knowledge by tag

Self-Improvement (6):

ToolPurpose
self_error_logLog structured errors for pattern analysis
self_insightManage insights (add/upvote/downvote/promote)
self_rulesManage behavioral rules (list/fire/rate/suspend)
self_patternsAnalyze error patterns and improvement trends
self_reflectSave session reflections
self_rules_contextLoad active rules at session start

Knowledge Graph (4):

ToolPurpose
memory_graphTraverse knowledge graph from a record
memory_conceptsDiscover concept clusters
memory_graph_indexRebuild graph index
memory_graph_statsGraph metrics (nodes, edges, density)

Episodic Memory (2):

ToolPurpose
memory_episode_saveSave rich session episodes
memory_episode_recallRecall episodes by semantic search

Skills & Competencies (3):

ToolPurpose
memory_skill_getGet skill level and history
memory_skill_updateUpdate skill level with tracking
memory_self_assessSelf-assessment across all skills

Advanced (5):

ToolPurpose
memory_observeLightweight file change tracking (30-day retention)
memory_associateAssociative search across knowledge
memory_context_buildBuild full task context in one call
memory_reflect_nowOn-demand reflection and insight synthesis
memory_extract_sessionProcess pending session transcripts

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
47
Repository forks
12
7-day trend score
19

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/vbcherepanov/total-agent-memory/codex-skill/badge)](https://verified-skill.com/skills/vbcherepanov/total-agent-memory/codex-skill)

Something wrong with this skill or its page? Tell us.