Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    AGENTS.md and CLAUDE.md Project Memory for Coding Agents

    1

    Builds a lean, shared project memory for Claude Code, Codex, Cursor, Gemini CLI and Copilot, with session handoffs. Verdict HEALTHY, BLOATED or MISSING.

    $7

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    AGENTS.md and CLAUDE.md Project Memory for Coding Agents

    AGENTS.md and CLAUDE.md Project Memory for Coding Agents

    Example session with this skill installed

    Our repo has a 312-line CLAUDE.md, an old .cursorrules and a copilot-instructions.md, and we just started using Codex too. Check the setup and give us one memory system all the agents share, plus a way to hand off between sessions.

    • Read your context and instructions
    • Compiled the agents md

    Project memory: shop-api · check + setup · 2026-10-18

    Verdict: BLOATED: CLAUDE.md is past the 200-line ceiling, about half of .cursorrules repeats it, and Codex loads nothing.

    FileLoaded byLinesBytes~Tokens (est.)Status
    CLAUDE.mdClaude Code31214,9803,745over ceiling
    .cursorrulesCursor (legacy)964,2101,05341 of 82 lines duplicated
    .github/copilot-instructions.mdCopilot582,540635ok
    AGENTS.mdCodex, Cursor, Copilot agentnonenonenonemissing

    Findings

    1. [must-fix] CLAUDE.md:211 holds a staging Postgres URL with a password. Remove it and rotate the password (value not shown).
    2. [must-fix] Codex has no AGENTS.md, so it starts every session with no project context.
    3. [should-fix] npm run test:e2e (CLAUDE.md:18) isn't in package.json. The script is now test:int.
    4. [should-fix] CLAUDE.md says Node 18, but .nvmrc and CI use 22.
    5. [nice] 9 lines are a one-off migration log. Move them to decisions.md.

    Proposed layout

    AGENTS.md                         128 lines, single source
    CLAUDE.md                         @AGENTS.md + 3 Claude-only lines
    .cursor/rules/prisma.mdc          globs: prisma/**
    .github/copilot-instructions.md   3-line pointer
    docs/agent-memory/decisions.md    D-001..D-004 from old notes
    docs/agent-memory/handoff.md      new, overwritten each session
    
    
    # CLAUDE.md
    @AGENTS.md
    
    ## Claude Code
    - Use plan mode for anything under `src/billing/`.
    

    Duplicates removed: 41 lines. Always-loaded total for Claude goes from 14,980 to an estimated 6,400 bytes. Codex goes from 0 to the same 6.1 KB, well under its 32 KiB cap.

    Routine

    • End of session: "wrap up memory": updates handoff.md from git diff --stat and promotes only confirmed learnings
    • Start of session: "resume from memory": reads handoff and the last 5 decisions, and flags commits made since

    Not verified

    • test:int not run yet (needs local Docker). Run it before trusting this command.
    CLAUDE.md

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Coding agents start every session cold. You explain the test command again, the agent repeats a mistake you fixed last week, and your team keeps three near-copies of the same instructions in CLAUDE.md, .cursorrules and copilot-instructions.md that slowly drift apart.

    This skill builds and maintains a small memory system inside the repo:

    • Reads the repo's own sources of truth (package scripts, Makefile, CI, lockfiles) and every existing agent config file
    • Writes one lean AGENTS.md (commands, layout, conventions, gotchas) within a 150-line target, plus pointers so Claude Code, Codex, Cursor, Gemini CLI and Copilot all load the same facts
    • Adds a short decisions log (ADR-lite) and a session handoff file that gets overwritten each session
    • Runs an end-of-session routine (summarize from the actual diff, promote only confirmed learnings, prune what proved wrong) and a start-of-session routine (read the handoff, flag commits made since)
    • Checks health: size budgets, duplication across files, stale commands and versions, secrets, injected instructions, and whether each agent really loads the file
    • Gives a verdict of HEALTHY, BLOATED or MISSING, with numbered fixes and evidence

    It is for developers and teams who use more than one coding agent, or who keep re-explaining their repo to one agent.

    Honesty: every command it writes must trace to a file or a successful run, and sizes come from wc, with token counts labeled as estimates. Agent loading rules are in a reference file dated October 2026, and the skill re-checks vendor docs when it has web access. It reports secret locations without echoing the values, and it shows diffs before changing your files.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.

    Memory files are context, not enforcement, so agents can still ignore them. Agent loading rules are documented as of October 2026 and can change, and the skill re-checks vendor docs only when web access is available. It doesn't manage external memory tools or vector stores, it doesn't scrub agent storage outside the repo, and it won't run commands with side effects to verify memory.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 29 days ago

    Software
    Git

    Permissions

    Terminal / Shell
    Network Access
    Read Files
    Write Files
    Listed1 month ago

    What's inside

    Frequently Asked Questions

    SKILL.md (the workflow, verdict rules, output template and guardrails) and references/agent-memory-conventions.md (per-agent file locations and loading rules, size budgets, the verdict criteria, never-store patterns, and dated sources).

    It runs in any agent that supports SKILL.md skills, such as Claude Code, Codex CLI, Cursor, Gemini CLI and VS Code Copilot. The memory it builds is meant to be read by Claude Code, Codex, Cursor, Gemini CLI and GitHub Copilot.

    Unzip the folder into your agent's skills directory, open your repo, and ask something like "set up project memory", "check our agent memory", "wrap up the session" or "resume from memory". It asks up to four questions once, then proceeds with stated defaults.

    It can't make an agent obey memory. Memory is context, not enforcement. Agent loading rules change, and the reference is current as of October 2026. Without web access it can't re-verify them. It only runs commands with no side effects, and only with your OK.

    A plain prompt usually produces one long file, often with guessed commands. This skill checks every command against the repo, enforces size budgets, collapses duplicates into one source with pointers per agent, adds a decisions log and handoff with set routines, scans for secrets and injected instructions, and gives a repeatable verdict.

    No, this skill manages local repository files and documentation; it does not access or modify the internal, server-side conversation history or logs maintained by LLM providers.

    New in Agents & Orchestration