Neat-Freak Knowledge Closeout
KKKKhazix/khazix-skills
Brings project docs, agent rule files, authorized memory and leftover workspace files back in line with what the code and runtime actually do at the end of a work session.
A skill your agent uses when a project's CLAUDE.md has grown past what anyone reads and you want the agent to learn durable facts from its own sessions instead — or when asking why the agent keeps…
Install Agent Memory
$ npx skills add alirezarezvani/claude-skills --skill agent-memory -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install alirezarezvani/claude-skills agent-memory --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/alirezarezvani/claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/engineering/agent-memory/skills/agent-memory .claude/skills/agent-memory && rm -rf skills-srcUse ~/.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/
Install the "agent-memory" agent skill from https://github.com/alirezarezvani/claude-skills/tree/main/engineering/agent-memory/skills/agent-memory into .claude/skills/agent-memory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-memory", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/alirezarezvani/claude-skills/tree/main/engineering/agent-memory/skills/agent-memoryType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add alirezarezvani/claude-skills --skill agent-memory -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install alirezarezvani/claude-skills agent-memory --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/alirezarezvani/claude-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/engineering/agent-memory/skills/agent-memory .agents/skills/agent-memory && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "agent-memory" agent skill from https://github.com/alirezarezvani/claude-skills/tree/main/engineering/agent-memory/skills/agent-memory into .agents/skills/agent-memory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-memory", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add alirezarezvani/claude-skills --skill agent-memory -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install alirezarezvani/claude-skills agent-memory --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/alirezarezvani/claude-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/engineering/agent-memory/skills/agent-memory .cursor/skills/agent-memory && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "agent-memory" agent skill from https://github.com/alirezarezvani/claude-skills/tree/main/engineering/agent-memory/skills/agent-memory into .cursor/skills/agent-memory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-memory", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/alirezarezvani/claude-skills.git --path engineering/agent-memory/skills/agent-memory--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add alirezarezvani/claude-skills --skill agent-memory -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install alirezarezvani/claude-skills agent-memory --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/alirezarezvani/claude-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/engineering/agent-memory/skills/agent-memory .gemini/skills/agent-memory && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "agent-memory" agent skill from https://github.com/alirezarezvani/claude-skills/tree/main/engineering/agent-memory/skills/agent-memory into .gemini/skills/agent-memory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-memory", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install alirezarezvani/claude-skills agent-memoryInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add alirezarezvani/claude-skills --skill agent-memory -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/alirezarezvani/claude-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/engineering/agent-memory/skills/agent-memory .github/skills/agent-memory && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "agent-memory" agent skill from https://github.com/alirezarezvani/claude-skills/tree/main/engineering/agent-memory/skills/agent-memory into .github/skills/agent-memory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-memory", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add alirezarezvani/claude-skills --skill agent-memory -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install alirezarezvani/claude-skills agent-memory --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/alirezarezvani/claude-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/engineering/agent-memory/skills/agent-memory .opencode/skills/agent-memory && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "agent-memory" agent skill from https://github.com/alirezarezvani/claude-skills/tree/main/engineering/agent-memory/skills/agent-memory into .opencode/skills/agent-memory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-memory", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
agent-memory- GitHub stars
- 28k
- Token cost
- ~1.3k tokens
- SKILL.md length
- 519 words
- Files
- 10 (incl. scripts, references, assets)
- Skills in repo
- 342
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when a project's CLAUDE.md has grown past what anyone reads and you want the agent to learn durable facts from its own sessions instead — or when asking why the agent keeps…
- Works in 5 steps: Redact before writing. Every atom passes… → Propose, never apply. Promotions land in… → Cite, don't invent. Every atom carries a… → …
- A projects CLAUDE.md has grown past what anyone reads and you want the agent to learn durable facts from its own sessions instead —
- SKILL.md covers The problem, The four tiers, The gates and Use it, plus 2 more sections
- Runs Python scripts from its folder; calls python3
What it does
Agent Memory is an agent skill from alirezarezvani/claude-skills. Use when a project's CLAUDE.md has grown past what anyone reads and you want the agent to learn durable facts from its own sessions instead — or when asking why the agent keeps re-learning the same correction, why a remembered rule is wrong, or where a memory line came from. Implements a four-tier store (L0 transcripts / L1 candidates / L2 project context / L3 stable persona) where promotion is earned by recurrence across sessions and days, never by one confident statement, and nothing reaches a committed file…
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 12 other files, including scripts, reference files and assets (for example `assets/memory_schema.json`, `references/hook_capture_discipline.md` and `references/promotion_gate_design.md`).
It sits in Agent Workflows, covering Agent memory and Agent instruction files. The repository describes itself as: 380 Claude Code skills & agent skills & plugins (30+ Agents, 70+ custom commands, 380+ skills, customizable references, scripts)for Claude Code, Codex, Gemini CLI, Cursor, and 8… The licence is MIT.
When your agent uses it
- A projects CLAUDE.md has grown past what anyone reads and you want the agent to learn durable facts from its own sessions instead —
- Asking why the agent keeps re-learning the same correction
- Why a remembered rule is wrong
- Where a memory line came from
Example prompts
- “/agent-memory”
Requirements
- Python 3
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Redact before writing. Every atom passes the filter before it reaches
- Propose, never apply. Promotions land in .memory/staged/. Only an
- Cite, don't invent. Every atom carries a back-pointer to the transcript
- Never surface a contested claim as fact. It is still injected — hiding
- The committed tiers carry no paths. Promotion strips the back-pointer
What it can do on your machine
Read from SKILL.md and the folder at commit 19392f7. 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
Ships 5 files in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
python3
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
Agent Memory loads about 1.3k tokens when it runs, and up to ~6.6k if it reads all its reference files. Until then it costs about 139 tokens; SKILL.md has 519 words of instructions outside code blocks.
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); the scripts in this folder are not scanned.
SKILL.md
The full file from alirezarezvani/claude-skills at commit 19392f7, republished under its MIT licence (© alirezarezvani). 519 words, ~1,297 tokens.
Download SKILL.mdSave it as
.claude/skills/agent-memory/SKILL.md (or your agent's skills folder). This skill also uses 9 other files; get the full folder from GitHub.- name
- agent-memory
- description
- Use when a project's CLAUDE.md has grown past what anyone reads and you want the agent to learn durable facts from its own sessions instead — or when asking why the agent keeps re-learning the same correction, why a remembered rule is wrong, or where a memory line came from. Implements a four-tier store (L0 transcripts / L1 candidates / L2 project context / L3 stable persona) where promotion is earned by recurrence across sessions and days, never by one confident statement, and nothing reaches a committed file without a human adopting it.
- argument-hint
- [optional: status | why "<claim>" | a tier name]
- license
- MIT
- metadata.version
- 1.0.0
- metadata.build_pattern
- Tencent TencentDB-Agent-Memory's tiering concept rebuilt natively on Claude Code hooks; deterministic recurrence gates, no LLM, no database
- metadata.distinct_from
- llm-wiki (a vault you write on purpose; this writes itself from sessions); skillopt-sleep (replays tasks to improve a skill; this extracts facts to remember)…
Agent Memory — promotion is earned, not asserted
Portability: stdlib only. No database, no embeddings, no network, no LLM calls.
The problem
A project's CLAUDE.md is a memory system with one tier and no eviction: every
durable fact and every passing preference land in the same always-loaded file,
until the important lines are diluted by the incidental ones. Facts learned
mid-session vanish at teardown unless someone writes them down.
The fix is not more storage — it is a promotion ladder. A claim earns its way toward always-loaded context by recurring; a human confirms the last step.
The four tiers
Tiers are distinguished by injection policy, not storage format.
| Tier | Holds | Injected | Committed |
|---|---|---|---|
| L0 | raw session transcripts | never | no (already on disk) |
| L1 | candidate atoms | on relevance, at prompt time | no (gitignored) |
| L2 | this project's context | every session start | yes, after adopt |
| L3 | stable cross-project persona | always | yes, after adopt |
The gates
Nothing moves up because it sounded important. It moves up because it recurred.
- L0 → L1 — an explicit marker fires (a directive, a correction, a stated preference, a named lesson, a reproducible failure). Rule-based, high precision, deliberately low recall.
- L1 → L2 — ≥ 3 distinct sessions spanning ≥ 2 distinct calendar days. A claim stated outright needs 2 sessions; the distinct-day rule still applies. A verified claim promotes on one observation and is the only day-exempt path.
- L2 → L3 — held in ≥ 2 distinct projects, aged ≥ 30 days, uncontested.
Two gates refuse rather than guess. A claim whose text was altered by redaction never promotes on evidence alone — the flag firing is evidence the source was sensitive, and a lexical filter finding one secret is not proof it found all of them. A claim with an open contradiction is frozen at L1 until a human resolves it; the incumbent is never silently overwritten.
Show full SKILL.md (221 more words)Show less
Use it
# what is remembered, and what is blocking the next promotion
python3 scripts/memory_inspect.py --tier L1
# where did this line come from — sessions, days, transcript, quoted source
python3 scripts/memory_inspect.py --why "PR base branch is dev"
# every claim with an open contradiction, both directions of the join
python3 scripts/memory_inspect.py --contested
# dry-run the promotion pass; writes nothing
python3 scripts/memory_promote.pyThree hooks run the loop unattended: SessionStart injects L2 + L3,
UserPromptSubmit recalls relevant L1 atoms, SessionEnd captures and stages.
Each is disabled independently with AGENT_MEMORY_SESSIONSTART=0,
AGENT_MEMORY_USERPROMPTSUBMIT=0, AGENT_MEMORY_SESSIONEND=0. Every hook fails
open: a broken memory system costs you memory, never a session.
Hard rules
- Redact before writing. Every atom passes the filter before it reaches disk. Anything altered is quarantined from promotion.
- Propose, never apply. Promotions land in
.memory/staged/. Only an explicit/cs:memory adopttouches aCLAUDE.md, and it backs both up first. - Cite, don't invent. Every atom carries a back-pointer to the transcript
line that produced it.
--whyresolving to ambiguous prints nothing rather than guess: a wrong citation is worse than a missing one. - Never surface a contested claim as fact. It is still injected — hiding the conflict is worse — but always tagged.
- The committed tiers carry no paths. Promotion strips the back-pointer prefix, which embeds an OS username.
Forcing questions
Walk these one at a time before trusting the store.
- Which line in your
CLAUDE.mddid you last actually read before acting? - Would you rather the agent forget a true thing, or remember a false one?
- When two remembered rules disagree, who decides — and when?
- What would make you delete
.memory/entirely?
Rationale, open decisions, field schema: ../../DESIGN.md.
© alirezarezvani, 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 9 other files (scripts, references, assets) in engineering/agent-memory/skills/agent-memory of alirezarezvani/claude-skills.
- SKILL.md
- assets/memory_schema.json
- references/hook_capture_discipline.md
- references/promotion_gate_design.md
- references/tiered_memory_canon.md
- scripts/memory_core.py
- scripts/memory_extract.py
- scripts/memory_inspect.py
- scripts/memory_promote.py
- scripts/validate_examples.py
Open the folder on GitHubat commit 19392f7
Compare with similar skills
Agent Memory 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Agent Memory this skillalirezarezvani/claude-skills | 28k | — | ~1.3k | Automated safety check: Pass | MIT | |
| Neat-Freak Knowledge CloseoutKKKKhazix/khazix-skills | 21k | — | ~1.9k | Automated safety check: Pass | MIT | |
| SkillOpt Sleep Cyclemicrosoft/SkillOpt | 18k | — | ~2.3k | Automated safety check: Pass | MIT | |
| CLAUDE.md Improveranthropics/claude-plugins-official | 37k | 5 repos | ~1.5k | Automated safety check: Pass | Apache-2.0 | |
| Harness Engineering10xChengTu/harness-engineering | 102 | 1 repos | ~1k | Automated safety check: Pass | None | |
| Codebase Analyzerseverity1/claude-code-auto-memory | 159 | — | ~1.5k | Automated safety check: Pass | MIT |
Similar skills
- Official
SkillOpt Sleep Cycle
microsoft/SkillOpt
Runs an on-demand or nightly sleep cycle that reviews past Claude Code sessions and proposes validated updates to CLAUDE.md and skills.
- Official
CLAUDE.md Improver
anthropics/claude-plugins-official
Finds every CLAUDE.md file in a repository, scores each against quality criteria, shows a report, then makes targeted updates after you approve.
Harness Engineering
10xChengTu/harness-engineering
Set up and improve harness engineering (AGENTS.md, docs/, lint rules, eval systems, project-level prompt engineering) for AI-agent-friendly codebases.
Codebase Analyzer
severity1/claude-code-auto-memory
This skill should be used when the user asks to "initialize auto-memory", "create CLAUDE.md", "set up project memory", or runs the /auto-memory:init command.
Self Improving For Codex
GODGOD126/self-improving-for-codex
Build or maintain a Codex-native self-improving memory loop using global AGENTS.md, a persistent memories directory, and optional nightly refinement automation.
More from alirezarezvani/claude-skills
All 342 skills in this repoAgile Product Owner
alirezarezvani/claude-skills
Writes INVEST-checked user stories with acceptance criteria, splits epics, plans sprints from velocity and ranks the backlog with a weighted score.
Product Strategist
alirezarezvani/claude-skills
OKR cascade toolkit for product leaders: generates aligned company-to-team OKRs from five strategy types and scores how well they line up.
App Store Optimization
alirezarezvani/claude-skills
App Store Optimization (ASO) toolkit for researching keywords, analyzing competitor rankings, generating metadata suggestions, and improving app visibility on Apple App Store and Google Play Store.
AWS Solution Architect
alirezarezvani/claude-skills
Design AWS architectures for startups using serverless patterns and IaC templates.
Campaign Analytics
alirezarezvani/claude-skills
Calculates attribution, funnel and ROI figures for marketing campaigns with three Python scripts that need only the standard library.
Code to PRD
alirezarezvani/claude-skills
Reverse-engineers a frontend, backend or fullstack codebase into a product requirements document with per-page docs, an enum dictionary and an API inventory.
Related
Categories
Questions about Agent Memory
What does Agent Memory do?
A skill your agent uses when a project's CLAUDE.md has grown past what anyone reads and you want the agent to learn durable facts from its own sessions instead — or when asking why the agent keeps…. Agent Memory is an agent skill from alirezarezvani/claude-skills.md has grown past what anyone reads and you want the agent to learn durable facts from its own sessions instead — or when asking why the agent keeps re-learning the same correction, why a remembered rule is wrong, or where a memory line came from.
When should I use Agent Memory?
Agent Memory fits situations like: A projects CLAUDE.md has grown past what anyone reads and you want the agent to learn durable facts from its own sessions instead —; asking why the agent keeps re-learning the same correction; why a remembered rule is wrong; where a memory line came from.
How do I install Agent Memory in Claude Code?
Run `npx skills add alirezarezvani/claude-skills --skill agent-memory -a claude-code`. Or copy the skill folder (engineering/agent-memory/skills/agent-memory in alirezarezvani/claude-skills) into .claude/skills/agent-memory in your project. Claude Code loads it when a task matches its description.
How do I install Agent Memory in Codex?
Run `npx skills add alirezarezvani/claude-skills --skill agent-memory -a codex`. Or copy the skill folder (engineering/agent-memory/skills/agent-memory in alirezarezvani/claude-skills) into .agents/skills/agent-memory in your project. Codex loads it when a task matches its description.
Can I use Agent Memory 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 alirezarezvani/claude-skills --skill agent-memory -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-memory, .gemini/skills/agent-memory, .github/skills/agent-memory and .opencode/skills/agent-memory in your project.
What does Agent Memory need to run?
Going by SKILL.md and its folder, Agent Memory needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.
Does Agent Memory 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 Agent Memory 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Agent Memory use?
Agent Memory is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Agent Memory use?
About 1.3k tokens (SKILL.md is roughly 5.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 5.3k tokens, read only when the agent opens those files.
What are the alternatives to Agent Memory?
Skills that share tags, products or a category with Agent Memory: Neat-Freak Knowledge Closeout (KKKKhazix/khazix-skills, 21k stars), SkillOpt Sleep Cycle (microsoft/SkillOpt, 18k stars), CLAUDE.md Improver (anthropics/claude-plugins-official, 37k stars) and Harness Engineering (10xChengTu/harness-engineering, 102 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Agent Memory?
alirezarezvani (a GitHub user) maintains it in alirezarezvani/claude-skills, which has 27,788 GitHub stars. The repository holds 342 skills in this directory. The repository was last updated on August 30, 2026.
Source: alirezarezvani/claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.