memory

A cross-session memory system that stores project knowledge and recalls it in later coding-agent sessions.

In plain words
What is it for?
It is for remembering project rules, past decisions, bug fixes, setup details, and remaining work across sessions and agents.
Why use it?
It reduces repeated explanations and helps preserve decisions, fixes, and lessons after a session ends.

Skill for Claude CodeCodex

Part of the total-agent-memory plugin — 3 skills, 7 hooks, 1 MCP server shipped together

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/vbcherepanov/total-agent-memory/codex-skill
Any agent
npx skills add vbcherepanov/total-agent-memory --skill codex-skill
Clone the repo
git clone --depth 1 https://github.com/vbcherepanov/total-agent-memory

Made for: Claude Code, Codex.

Or install total-agent-memory, the plugin that ships this one along with the rest of its 3 skills, 7 hooks, 1 MCP server.

Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,241 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 $0.00065 $0.01241
Opus 5 $0.00032 $0.00620
Sonnet 5 $0.00013 $0.00248
Haiku 4.5 $0.00006 $0.00124

Measured 3d ago against content hash 7095fa55c3d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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.

codex-skill/SKILL.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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.

Event type What to save
Architectural decision decision Decision + WHY + rejected alternatives
Non-trivial bug fix solution Symptom -> root cause -> fix
Gotcha or pitfall discovered lesson Expected vs actual + takeaway
Infrastructure or config setup fact Config details + key parameters
Project pattern established convention Rule + code example
Session ending fact Summary 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

Read the full file on GitHub · 155 lines

Files

What ships with it

1 file 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. 3d ago First seen · 155 lines · 65 tokens per session scan A 7095fa55c3d1

Subscribe to this mod's changes

memory is a skill published in the GitHub repository vbcherepanov/total-agent-memory (66 stars, last pushed 6d ago), licensed MIT. It adds 65 tokens to every session and 1,241 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

mulch-record-from-evidence

Turn the evidence of a finished work session — git commits, changed files, recently-touched seeds issues — into well-formed ml record invocations. Use at session close, when an agent has made changes worth preserving as mulch expertise but hasn't yet recorded them.

jayminwest/mulch · 61 tokens

implement

End-to-end workflow for taking MCP work items from backlog to merged PR. Handles git branching, schema-driven planning, implementation, independent review, and PR creation. Composes spec-quality, review-quality, and schema-workflow skills into a single pipeline. Use when a user says "implement this", "work on this…

jpicklyk/task-orchestrator · 101 tokens

session-retrospective

Analyzes the current implementation run — evaluates schema effectiveness, delegation alignment, note quality, and plan-to-execution fit. Captures cross-session trends and proposes improvements when patterns repeat. Use after implementation runs, or when user says 'retrospective', 'session review', 'what did we learn'…

jpicklyk/task-orchestrator · 107 tokens

ralph

Launcher for the Ralph-style queue drain script — emits the right node ralph-loop.mjs invocation based on the user's filter and bounds. The actual loop runs as a Node script that spawns one claude -p --worktree per iteration; this skill is the configurator, not the loop. Use when a user says: drain the backlog, ralph…

jpicklyk/task-orchestrator · 99 tokens

prepare-release

End-to-end release automation — reads commits since last tag, infers semver bump, drafts changelog, creates release PR, merges it, waits for CI green, tags, and monitors the Docker build to completion. Use when the user says: prepare release, cut a release, bump version, create release PR, ship a new version, tag a…

jpicklyk/task-orchestrator · 95 tokens

quick-start

Interactive onboarding for the MCP Task Orchestrator. Detects empty or populated workspaces and walks through how plan mode, persistent tracking, and the MCP work together. Use when a user says "get started", "how do I use this", "quick start", "first time setup", "onboard me", "what can this MCP do", or "help me…

jpicklyk/task-orchestrator · 82 tokens