unforgit-memory

unforgit-memory is a skill for Claude Code, Codex from MiguelMedeiros/unforgit. It costs 27 tokens per session (573 once invoked), scanned A, original, MIT.

A set of instructions for using Unforgit as long-term memory for a code repository.

In plain words
What is it for?
Use it during substantial coding, planning, debugging, releases, or reviews to recall context and save durable project knowledge.
Why use it?
It helps an agent recall earlier context and preserve important decisions, conventions, bugs, and procedures.

Skill for Claude CodeCodex

Part of the unforgit plugin — 1 skill, 5 commands, 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/miguelmedeiros/unforgit/unforgit-memory
Any agent
npx skills add MiguelMedeiros/unforgit --skill unforgit-memory
Clone the repo
git clone --depth 1 https://github.com/MiguelMedeiros/unforgit

Made for: Claude Code, Codex.

Or install unforgit, the plugin that ships this one along with the rest of its 1 skill, 5 commands, 1 MCP server.

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 unforgit-memory

README.md
[![agentmods](https://agentmods.dev/badge/skills/miguelmedeiros/unforgit/unforgit-memory.svg)](https://agentmods.dev/skills/miguelmedeiros/unforgit/unforgit-memory)
Your own site
<a href="https://agentmods.dev/skills/miguelmedeiros/unforgit/unforgit-memory"><img src="https://agentmods.dev/badge/skills/miguelmedeiros/unforgit/unforgit-memory.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 573 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 $0.00027 $0.00573
Opus 5 $0.00014 $0.00287
Sonnet 5 $0.00005 $0.00115
Haiku 4.5 $0.00003 $0.00057

Measured 4d ago against content hash 1b52d6e765f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

unforgit-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 4d 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.

plugins/claude-code/unforgit/skills/unforgit-memory/SKILL.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Unforgit Memory

Use this skill whenever work can benefit from durable project memory or when the user asks you to remember, recall, curate, or inspect repository knowledge.

Core workflow

  1. Recall first for substantive work. At the start of non-trivial coding, planning, debugging, release, or review work, call unforgit_recall with a query based on the user's request and the repository area being touched.
  2. Use recalled context. Apply prior decisions, conventions, gotchas, and playbooks before changing code or proposing a plan.
  3. Save durable context promptly. When a stable decision, convention, gotcha, bug pattern, workaround, API contract, or reusable procedure emerges, call unforgit_add with concise self-contained text.
  4. Curate when memory quality matters. Use unforgit_health, unforgit_sync_status, unforgit_find_similar, unforgit_consolidate, and unforgit_curate when diagnosing memory quality, duplicates, sync, or stale notes.

What to save

  • semantic: stable facts, architectural decisions, conventions, API contracts.
  • procedural: repeatable workflows, release/deploy playbooks, troubleshooting steps.
  • episodic: notable bugs, gotchas, one-off observations that may prevent future mistakes.

What not to save

  • Do not save secrets, tokens, passwords, API keys, private credentials, or sensitive environment values.
  • Do not save temporary progress, task checklists, transient logs, command output dumps, PR numbers, commit SHAs, or facts likely to be stale soon.
  • Do not save obvious information already documented in the repository unless the memory captures a decision or gotcha not obvious from the code.

Writing guidelines

  • Write memory text in English unless the repository explicitly standardizes another language.
  • Keep each memory concise but self-contained.
  • Use tags such as auth, api, deploy, bug, gotcha, decision, or package/module names.
  • Prefer repository-scoped Unforgit memory over global assistant memory for project-specific knowledge.
  • If a memory may duplicate an existing one, search first and consolidate rather than creating noise.

Read the full file on GitHub · 43 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. 4d ago First seen · 43 lines · 27 tokens per session scan A 1b52d6e765f9

Subscribe to this mod's changes

unforgit-memory is a skill published in the GitHub repository MiguelMedeiros/unforgit (9 stars, last pushed yesterday), licensed MIT. It adds 27 tokens to every session and 573 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

kb

Set up, evolve, or operate a hraness/kb local-first Markdown knowledge base for coding-agent memory. Use when a user asks to design KB conventions or a recurring KB ritual; search or query a KB or Obsidian vault; load or recover repository context, plans, decisions, concepts, backlinks, semantic search, or Git…

hraness/kb · 155 tokens

acontext-installer

Install Acontext, Login & Init Acontext Project, Add Skill Memory to Agent.

memodb-io/Acontext · 22 tokens

argon-memory

Use an Argon Memory MCP server for durable project context, evidence-grounded retrieval, artifacts, work closeout, and conflict-aware memory.

Tangtaizong-BUAA/ArgonMemory · 31 tokens

exomem

Use when working with Exomem — your personal knowledge base (a markdown vault, Obsidian optional, of raw sources, compiled research notes, insights, failures, patterns, experiments, production-logs, typed entities, and Evidence artifacts). Triggers whenever you name Exomem (the connector/MCP you talk to) or want to…

Artexis10/exomem · 203 tokens

agent-recall-trail

Recall and maintain one Agent's private, sourced experience together with human-reviewed shared ART Knowledge Editions. Use when prior decisions, procedures, project facts, user preferences, earlier failures, or reusable conclusions may affect the current task, and when the user asks to remember, retrieve, correct, or…

fantasyce/agent-recall-trail · 68 tokens

art-recall

Use Agent Recall Trail through its bound MCP tools when prior coding-agent experience or reviewed shared knowledge could materially change a decision. Governs recall, capture, reading, feedback, and proposals without bypassing ART storage or human review.

fantasyce/agent-recall-trail · 49 tokens