A skill your agent uses when Wingman memory is already known enabled in the current repository and starting non-trivial coding, debugging, planning, review, API integration, or business-logic work…

Apache-2.0Auto-check passedBackend & APIs

Install Memory Load

skills CLI
$ npx skills add hashgraph-online/awesome-codex-plugins --skill memory-load -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install hashgraph-online/awesome-codex-plugins memory-load --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/lsshym/wingman.ai/skills/memory-load .claude/skills/memory-load && rm -rf skills-src

Use ~/.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/

Facts

Skill name
memory-load
GitHub stars
1.2k
Token cost
~1.7k tokens
SKILL.md length
908 words
Files
1
Skills in repo
686
Repo updated
First seen
Licence
Apache-2.0

At a glance

A skill your agent uses when Wingman memory is already known enabled in the current repository and starting non-trivial coding, debugging, planning, review, API integration, or business-logic work…

  • Works in 8 steps: Check memory state. → If memory is disabled or not needed,… → Read .wingman/memory/brief.md. → …
  • Wingman memory is already known enabled in the current repository and starting non-trivial coding
  • SKILL.md covers Memory State, Authority, When To Load and Load Protocol, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Memory Load is an agent skill from hashgraph-online/awesome-codex-plugins. Use when Wingman memory is already known enabled in the current repository and starting non-trivial coding, debugging, planning, review, API integration, or business-logic work, or when the user explicitly asks to load or read Wingman memory.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Backend & APIs, covering Third-party API integration. The repository describes itself as: A curated list of awesome OpenAI Codex / ChatGPT plugins, skills, and resources. The 1 Codex Marketplace. See live plugins at: https://hol.org/plugins/best-codex-plugins. The licence is Apache-2.0.

When your agent uses it

  • Wingman memory is already known enabled in the current repository and starting non-trivial coding
  • API integration
  • Business-logic work
  • The user explicitly asks to load

Example prompts

  • “/memory-load”

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

  1. Check memory state.
  2. If memory is disabled or not needed, continue without reading memory files.
  3. Read .wingman/memory/brief.md.
  4. Use the Domain Registry to choose relevant current domain truth.
  5. Read relevant domains/ files.
  6. Read .wingman/memory/context.md only for hot task state and direct pointers.
  7. Read history projections only when Historical-Risk Signals are present.
  8. Read at most 0-3 selected history event bodies by default.

What it can do on your machine

Read from SKILL.md and the folder at commit 78497e5. 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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    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

Memory Load loads about 1.7k tokens when it runs. Until then it costs about 64 tokens; SKILL.md has 908 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~64
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from hashgraph-online/awesome-codex-plugins at commit 78497e5, republished under its Apache-2.0 licence (© hashgraph-online). 908 words, ~1,740 tokens.

Download SKILL.mdSave it as .claude/skills/memory-load/SKILL.md (or your agent's skills folder).
name
memory-load
description
Use when Wingman memory is already known enabled in the current repository and starting non-trivial coding, debugging, planning, review, API integration, or business-logic work, or when the user explicitly asks to load or read Wingman memory.

Wingman Memory Load

memory-load is read-only. It loads current truth by default and history only when the task needs explanation or past-change context.

Memory State

Use .wingman/memory/ as the repository-local memory root.

Repository memory is enabled only when both core entry files exist:

text
.wingman/memory/brief.md
.wingman/memory/context.md

If .wingman/memory/ is missing, continue without memory unless the user explicitly asked about memory. If the directory exists but a core entry file is missing, report partial memory only when the user asked about memory or the task depends on memory consistency.

Authority

Use this authority order when memory files disagree:

text
brief.md current Project Decisions
> domains/ current truths
> context.md hot working state
> history/ past events and evidence

History explains why something changed. It is not current truth unless a current entry in brief.md or domains/ links to it as evidence.

Only Status: current current-truth entries are binding. candidate, deprecated, and superseded entries are background only.

Relations:

  • updates <id> replaces the referenced entry for overlapping scope.
  • extends <id> keeps both entries valid when compatible.
  • derived_from <id-or-path> records evidence lineage, not authority.

If two current entries with the same Subject conflict and no relation resolves them, stop and ask which rule is valid.

When To Load

Skip memory for trivial isolated work: typo-only edits, formatting, isolated style tweaks, throwaway experiments, or local changes with no business, state, data, contract, reuse, or existing-behavior impact.

Load memory before non-trivial coding, debugging, planning, review, refactor, API integration, reusable implementation work, or changes touching business logic, state flow, permissions, quotas, billing, field mappings, contracts, or existing behavior.

Also load memory when the user mentions previous work, consistency, "之前", "上次", "沿用", "保持一致", "不要破坏", or asks to use memory.

Load Protocol

  1. Check memory state.
  2. If memory is disabled or not needed, continue without reading memory files.
  3. Read .wingman/memory/brief.md.
  4. Use the Domain Registry to choose relevant current domain truth.
  5. Read relevant domains/ files.
  6. Read .wingman/memory/context.md only for hot task state and direct pointers.
  7. Read history projections only when Historical-Risk Signals are present.
  8. Read at most 0-3 selected history event bodies by default.

For folder domains, read the folder index.md first, then only the relevant subfiles named by that index. Do not read every domain subfile by default.

Domain Registry

The Domain Registry in brief.md is a routing table:

md
| Domain | Read When | Current File | History Domain Index | History Topics | Aliases | Related Domains | Status |
  • Current File points to current truth.
  • History Domain Index and History Topics point to historical lookup indexes.
  • Related Domains are hints, not automatic expansion.
  • Deprecated or superseded registry rows are not authoritative unless the replacement points there.

Read a current domain when the task matches Domain, Read When, or Aliases. Read related domains only when the task also touches that related area or the current domain file points to a specific related rule.

Context

context.md is a hot cache. Read it for:

  • active unfinished work;
  • pending follow-up;
  • blocker or debugging state needed soon;
  • direct pointer to current truth or history for the active task.

Treat context pointers as routing hints. If a pointer names a current truth, read that truth. If it names a history event, read the event only when Historical-Risk Signals are present or the pointer is directly needed for the task.

Show full SKILL.md (400 more words)Show less

Historical-Risk Signals

Read history projections only when at least one signal is present:

  • the user asks about previous work, "before", "last time", "why", "what changed", "之前", or "上次";
  • the task changes or depends on rule semantics, field meanings, state flows, API contracts, business meaning, or agent behavior;
  • current truth links to a history event and the reason matters for the task;
  • a context pointer directly names a relevant history event;
  • history is needed to avoid repeated debugging or repeated wrong interpretation.

When history is needed, prefer sources in this order:

  1. Direct event links from current truth or context pointers.
  2. history/topics/<topic>.md.
  3. history/domains/<domain>.md.
  4. history/months/YYYY-MM.md for date questions.
  5. history/index.md when projection routing is unclear or the user asks broadly.

Choose only the strongest 0-3 event bodies for the current task unless the user asks for deeper history.

Do not scan history/events/ directly by default.

Internal Checklist

Before editing code, internally confirm:

  • active task and relevant files;
  • memory files read;
  • relevant current truth IDs and subjects;
  • any candidate, deprecated, or superseded entries;
  • any relation targets needed to understand the current rule;
  • history projections or event bodies read, if any;
  • exact fields, symbols, contracts, or rules that are binding;
  • whether the requested change conflicts with memory.

Do not show the checklist by default. Surface it only when there is a conflict, missing context, or the user asks.

Memory Pressure Signals

memory-load may notice memory pressure but must not clean, compact, summarize, promote, or delete memory.

Mention cleanup only when a concrete candidate affects the task:

  • context.md contains durable rule bodies instead of pointers;
  • context repeats bodies already owned by brief.md, domains/, or history/events/;
  • two current truths conflict;
  • a replaced rule is still marked current;
  • history projections copy event bodies instead of linking them;
  • relevant history exists but no topic or domain projection helps lookup.

Suggest explicit memory-clean later. If a conflict blocks correct work, ask the user which rule is valid.

Binding Rules

  • Never substitute one business field for a semantically different field for convenience.
  • If memory specifies a canonical field or contract, follow it unless the user changes the rule.
  • Treat existing // @invariant: comments as local binding context when present.
  • memory-load is read-only; new comments or memory updates belong to the relevant coding task or memory-sync.
  • Existing capability and reuse lookup belongs to project-map-find; do not read project-map files during memory-load unless the user explicitly asks for project-map context.

© hashgraph-online, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugins/lsshym/wingman.ai/skills/memory-load of hashgraph-online/awesome-codex-plugins.

Open the folder on GitHubat commit 78497e5

Compare with similar skills

Memory Load 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.

Memory Load compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Memory Load this skillhashgraph-online/awesome-codex-plugins1.2k—~1.7kAutomated safety check: PassApache-2.0
ToolJet Marketplace Plugin BuilderToolJet/ToolJet41k—~2.1kAutomated safety check: PassAGPL-3.0
WxJava API Contributorbinarywang/WxJava33k—~154Automated safety check: PassApache-2.0
Dominion Addon DevLunaDeerMC/Dominion134—~2.6kAutomated safety check: PassMIT
fp-go HTTP Client PatternsIBM/fp-go2k—~4.4kAutomated safety check: PassApache-2.0
Read The Damn DocsBuilderIO/skills4.5k—~1.8kAutomated safety check: PassMIT

Similar skills

  • Turns an API description, such as an OpenAPI file or a Postman collection, into a connector plugin for ToolJet's marketplace and checks it with the repo's validator.

    41k GitHub stars~2.1k tokensUpdated today
    Backend & APIsAuto-check passed
  • WxJava API Contributor

    binarywang/WxJava

    Steps for adding or maintaining a WeChat official API in the WxJava SDK, following its Maven multi-module layout, Java 8 compatibility and TestNG test conventions.

    33k GitHub stars~154 tokensUpdated 12 days ago
    Backend & APIsAuto-check passed
  • Dominion Addon Dev

    LunaDeerMC/Dominion

    Develop Dominion addon plugins using the DominionAPI. An agent skill from LunaDeerMC/Dominion.

    134 GitHub stars~2.6k tokensUpdated today
    Backend & APIsAuto-check passed
  • Official

    Shows how to build composable, context-aware HTTP pipelines in Go using fp-go's ReaderIOResult monad instead of raw net/http calls.

    2k GitHub stars~4.4k tokensUpdated yesterday
    Backend & APIsAuto-check passed
  • Read The Damn Docs

    BuilderIO/skills

    A skill your agent uses when implementing, integrating, upgrading, debugging, or answering anything involving third-party APIs, libraries, frameworks, CLIs, cloud services, model/provider SDKs…

    4.5k GitHub stars~1.8k tokensUpdated today
    Backend & APIsAuto-check passed
  • DisCatSharp Discord Development

    Aiko-IT-Systems/DisCatSharp

    Helps build, explain and troubleshoot C# Discord apps on DisCatSharp, answering from the project's installed version and the library's documentation rather than guesses.

    140 GitHub stars~1.2k tokensUpdated 2 days ago
    Backend & APIsAuto-check passed

More from hashgraph-online/awesome-codex-plugins

All 686 skills in this repo
  • Anime Reaction Gif

    hashgraph-online/awesome-codex-plugins

    Create original anime-style reaction stickers as looping GIFs and MP4 previews, using generated character pose sheets and timed key poses.

    1.2k GitHub stars~922 tokensUpdated today
    Auto-check passed
  • Calibredb

    hashgraph-online/awesome-codex-plugins

    Manage and query Calibre libraries with the calibredb CLI (local paths or Calibre Content server URLs).

    1.2k GitHub stars~1k tokensUpdated today
    Auto-check passed
  • Rust API Test Harness

    hashgraph-online/awesome-codex-plugins

    A skill your agent uses when adding, changing, testing, or debugging Rust HTTP APIs and services, especially when Codex needs black-box integration tests, random-port app startup, real database test…

    1.2k GitHub stars~1.7k tokensUpdated today
    Auto-check passed
  • Art

    hashgraph-online/awesome-codex-plugins

    Make a studio's game look like something at build time — a cover from a real frame of the game (free), painted covers, backdrops, textures and character plates from image models through the…

    1.2k GitHub stars~2.4k tokensUpdated today
    Auto-check passed
  • Game Balance Economy

    hashgraph-online/awesome-codex-plugins

    Balance game difficulty, resources, rewards, probability, progression, economies, and dominant strategies.

    1.2k GitHub stars~618 tokensUpdated today
    Auto-check passed
  • Manuscript Engagement Analytics

    hashgraph-online/awesome-codex-plugins

    Analyze nonfiction manuscripts for reader engagement signals, including heading-level word counts, slow starts, long slogs, weak takeaway titles, value pacing, beta-reader comment dropoff, and…

    1.2k GitHub stars~875 tokensUpdated today
    Auto-check passed

Questions about Memory Load

What does Memory Load do?

A skill your agent uses when Wingman memory is already known enabled in the current repository and starting non-trivial coding, debugging, planning, review, API integration, or business-logic work…. Memory Load is an agent skill from hashgraph-online/awesome-codex-plugins. Use when Wingman memory is already known enabled in the current repository and starting non-trivial coding, debugging, planning, review, API integration, or business-logic work, or when the user explicitly asks to load or read Wingman memory.

When should I use Memory Load?

Memory Load fits situations like: wingman memory is already known enabled in the current repository and starting non-trivial coding; API integration; business-logic work; the user explicitly asks to load.

How do I install Memory Load in Claude Code?

Run `npx skills add hashgraph-online/awesome-codex-plugins --skill memory-load -a claude-code`. Or copy the skill folder (plugins/lsshym/wingman.ai/skills/memory-load in hashgraph-online/awesome-codex-plugins) into .claude/skills/memory-load in your project. Claude Code loads it when a task matches its description.

How do I install Memory Load in Codex?

Run `npx skills add hashgraph-online/awesome-codex-plugins --skill memory-load -a codex`. Or copy the skill folder (plugins/lsshym/wingman.ai/skills/memory-load in hashgraph-online/awesome-codex-plugins) into .agents/skills/memory-load in your project. Codex loads it when a task matches its description.

Can I use Memory Load 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 hashgraph-online/awesome-codex-plugins --skill memory-load -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/memory-load, .gemini/skills/memory-load, .github/skills/memory-load and .opencode/skills/memory-load in your project.

What does Memory Load need to run?

SKILL.md names no scripts, command-line tools or credentials: Memory Load is instructions for the agent only.

Does Memory Load 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 Memory Load 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. Review the folder before installing.

What licence does Memory Load use?

Memory Load is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Memory Load use?

About 1.7k tokens (SKILL.md is roughly 7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Memory Load?

Skills that share tags, products or a category with Memory Load: ToolJet Marketplace Plugin Builder (ToolJet/ToolJet, 41k stars), WxJava API Contributor (binarywang/WxJava, 33k stars), Dominion Addon Dev (LunaDeerMC/Dominion, 134 stars) and fp-go HTTP Client Patterns (IBM/fp-go, 2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Memory Load?

hashgraph-online (a GitHub organization) maintains it in hashgraph-online/awesome-codex-plugins, which has 1,242 GitHub stars. The repository holds 686 skills in this directory. The repository was last updated on October 8, 2026.

Source: hashgraph-online/awesome-codex-plugins on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.