New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Memory Discipline

by Sidiora-Labs in Sidiora-Labs/centra-gideon-agent

When and how to persist durable memory — save genuine user preferences, facts, and corrections; NEVER persist transient environment failures (a failed command, a flaky network call, a one-off tool…

Apache-2.0Auto-check passedAI & LLM Engineering

Install Memory Discipline

skills CLI
$ npx skills add Sidiora-Labs/centra-gideon-agent --skill memory-discipline -a claude-code

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

GitHub CLI
$ gh skill install Sidiora-Labs/centra-gideon-agent memory-discipline --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/Sidiora-Labs/centra-gideon-agent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/runtime/gideon/extensions/skills/bundled/memory-discipline .claude/skills/memory-discipline && 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-discipline
GitHub stars
217
Token cost
~1.1k tokens
SKILL.md length
566 words
Files
1
Skills in repo
24
Repo updated
First seen
Licence
Apache-2.0

At a glance

When and how to persist durable memory — save genuine user preferences, facts, and corrections; NEVER persist transient environment failures (a failed command, a flaky network call, a one-off tool…

  • AI & LLM Engineering work in your project
  • SKILL.md covers What IS worth remembering, What is NOT a lesson (the key…, Recall before re-asking and How to write a good memory, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Memory Discipline is an agent skill from Sidiora-Labs/centra-gideon-agent. When and how to persist durable memory — save genuine user preferences, facts, and corrections; NEVER persist transient environment failures (a failed command, a flaky network call, a one-off tool error) as lessons; recall before re-asking.

Its SKILL.md is about 1.1k 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 AI & LLM Engineering. The repository describes itself as: The companion AI agent that learns, adapts and gets the work done no matter the task. The licence is Apache-2.0.

When your agent uses it

  • AI & LLM Engineering work in your project

Example prompts

  • “/memory-discipline”

What it can do on your machine

Read from SKILL.md and the folder at commit ca531ee. 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.

    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 Discipline loads about 1.1k tokens when it runs. Until then it costs about 65 tokens; SKILL.md has 566 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~65
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

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 Sidiora-Labs/centra-gideon-agent at commit ca531ee, republished under its Apache-2.0 licence (© Sidiora-Labs). 566 words, ~1,058 tokens.

Download SKILL.mdSave it as .claude/skills/memory-discipline/SKILL.md (or your agent's skills folder).
name
memory-discipline
description
When and how to persist durable memory — save genuine user preferences, facts, and corrections; NEVER persist transient environment failures (a failed command, a flaky network call, a one-off tool error) as lessons; recall before re-asking.
always
false
triggers
remember, memory, lesson, preference, note this, persist, save this for later, recall, forget, learned, you should know

Memory Discipline

Gideon is persistent and self-learning — across sessions it remembers what the user prefers, durable facts about them and their work, and corrections they've made. That value collapses if memory fills with noise. The discipline is simple: persist what's durable, recall before re-asking, and never store transient failures as lessons.

Tools: memory_remember (save), memory_recall / memory_list (retrieve), memory_forget (remove).

What IS worth remembering

Persist something only when it will still be true and useful next week, in a different session. Three durable kinds:

  • Preference — a standing choice about how the user wants things done. "Prefers pytest over unittest." "Wants concise answers, no preamble." "Uses tabs, not spaces, in this repo."
  • Fact — durable truth about the user, their environment, or their projects. "The prod database is orders-prod in us-east-1." "Their team's CI is GitHub Actions." "Deploys go out Tuesdays."
  • Correction — the user fixed something you got wrong; capture the corrected rule so you don't repeat the mistake. "Don't call it 'the API' — it's specifically the Billing API." "I said X was fine; the user corrected that X is forbidden here."

What is NOT a lesson (the key guardrail)

Never persist environment or transient failures as memory. A failure that belongs to this moment — not to the user's durable preferences or world — is not a lesson:

  • A bash command that failed (wrong flag, missing file, exit 1) — fix it and move on; don't remember "the command failed".
  • A flaky or timed-out network call, a transient API 500, a rate-limit — retry or route around; it's not a fact about the user.
  • A one-off tool error (bad argument, malformed path, a file that didn't exist yet) — correct the call; the error is not knowledge.
  • A momentary state ("the server was down", "the test was red just now") — state changes; don't freeze a snapshot of it into permanent memory.

Litmus test before memory_remember: "Will this still be true and actionable in a fresh session next week?" If it's about something that just broke or a passing condition of the current run, the answer is no — don't save it. (If a failure reveals a durable rule — e.g. "this build always needs Node ≥20" — save the rule, not the incident.)

Show full SKILL.md (203 more words)Show less

Recall before re-asking

Before asking the user something they may have already told you — a preference, a default, a name, an environment detail — check memory first with memory_recall (semantic lookup) or memory_list (browse). If it's there, act on it (or confirm — "Last time you preferred X; still the case?") instead of re-asking. Re-asking something already on record is exactly the friction persistent memory exists to remove.

How to write a good memory

  • One durable rule per entry, phrased as a standing instruction or fact, not a narration of an event. ✅ "Prefers TypeScript strict mode." ❌ "Today we turned on strict mode."
  • Categorize by kind (preference / fact / correction) and scope it appropriately — workspace/project-specific facts scoped to that project, global preferences scoped broadly — so recall surfaces the right thing in context.
  • Supersede, don't duplicate. If a new preference contradicts an old one, update/forget the stale entry rather than leaving both — contradictory memory is worse than none.

Don't

  • Don't save secrets or credential contents, ever.
  • Don't save throwaway working state (current branch, today's failing test, a transient error) — see the guardrail above.
  • Don't save something the user didn't actually express as durable just because it came up once; ephemeral context stays in the conversation, not in memory.

© Sidiora-Labs, 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 runtime/gideon/extensions/skills/bundled/memory-discipline of Sidiora-Labs/centra-gideon-agent.

Open the folder on GitHubat commit ca531ee

Compare with similar skills

Memory Discipline 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 Discipline compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Memory Discipline this skillSidiora-Labs/centra-gideon-agent217—~1.1kAutomated safety check: PassApache-2.0
Agent BuildershareAI-lab/learn-claude-code78k5 repos~1.2kAutomated safety check: PassMIT
Add Uint Supportpytorch/pytorch104k2 repos~2.3kAutomated safety check: PassCustom licence
LLM Benchmarking with lm-evaluation-harnessOrchestra-Research/AI-Research-SKILLs13k8 repos~3kAutomated safety check: PassMIT
Segment Anything Model GuideOrchestra-Research/AI-Research-SKILLs13k8 repos~3.3kAutomated safety check: PassMIT
1passwordtrpc-group/trpc-agent-go1.9k14 repos~656Automated safety check: PassApache-2.0

Similar skills

  • Agent Builder

    shareAI-lab/learn-claude-code

    Design and build AI agents for any domain. An agent skill from shareAI-lab/learn-claude-code.

    78k GitHub starsUsed in 5 repos~1.2k tokens
    AI & LLM EngineeringAuto-check passed

  • Add Uint Support

    pytorch/pytorch

    Add unsigned integer (uint) type support to PyTorch operators by updating ATDISPATCH macros.

    104k GitHub starsUsed in 2 repos~2.3k tokens
    AI & LLM EngineeringAuto-check passed

  • LLM Benchmarking with lm-evaluation-harness

    Orchestra-Research/AI-Research-SKILLs

    Runs lm-evaluation-harness to benchmark language models on academic suites such as MMLU, GSM8K and HumanEval, compare models and track training checkpoints.

    13k GitHub starsUsed in 8 repos~3k tokens
    AI & LLM EngineeringAuto-check passed

  • Segment Anything Model Guide

    Orchestra-Research/AI-Research-SKILLs

    Guide to using Meta's Segment Anything Model for zero-shot image segmentation with point, box or mask prompts, or automatic mask generation.

    13k GitHub starsUsed in 8 repos~3.3k tokens
    AI & LLM EngineeringAuto-check passed

  • 1password

    trpc-group/trpc-agent-go

    Set up and use 1Password CLI (op). An agent skill from trpc-group/trpc-agent-go.

    1.9k GitHub starsUsed in 14 repos~656 tokens
    AI & LLM EngineeringAuto-check passed

  • Planning With Files

    jarrodwatts/claude-code-config

    Transforms workflow to use Manus-style persistent markdown files for planning, progress tracking, and knowledge storage.

    1.1k GitHub starsUsed in 5 repos~967 tokens
    AI & LLM EngineeringAuto-check passed

More from Sidiora-Labs/centra-gideon-agent

All 24 skills in this repo

  • Artifacts

    Sidiora-Labs/centra-gideon-agent

    Persist, version, and iterate on LLM-generated UI (widgets, HTML, markdown).

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

  • Best Of N

    Sidiora-Labs/centra-gideon-agent

    Sample several candidate answers in parallel, judge them against stated criteria, and present the winner with the runners-up kept one click away.

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

  • Document Authoring

    Sidiora-Labs/centra-gideon-agent

    Author a real document — a report, proposal, slide deck, spec, or paper — by settling audience, claim, and structure before drafting prose, then writing to that structure.

    217 GitHub stars~970 tokensUpdated today
    Auto-check passed

  • Editorial Document

    Sidiora-Labs/centra-gideon-agent

    Write long-form editorial documents as clean, semantic HTML saved as an artifact (kind=document) — reports, briefs, explainers, proposals, write-ups.

    217 GitHub stars~1.3k tokensUpdated today
    Auto-check passed

  • Gideon API

    Sidiora-Labs/centra-gideon-agent

    The operator's manual for DRIVING Gideon's API and tools — how to find an exact tool/route signature, the mandatory verify-after-mutate loop, and what NOT to hand-roll.

    217 GitHub stars~1.4k tokensUpdated today
    Auto-check passed

  • Infographic Syntax

    Sidiora-Labs/centra-gideon-agent

    Author infographics with the AntV declarative DSL — pick a template, fill a small indented data tree, and save as an artifact (kind=infographic) that renders to crisp SVG and streams as you write it.

    217 GitHub stars~1.1k tokensUpdated today
    Auto-check passed

Categories

Questions about Memory Discipline

What does Memory Discipline do?

When and how to persist durable memory — save genuine user preferences, facts, and corrections; NEVER persist transient environment failures (a failed command, a flaky network call, a one-off tool…. Memory Discipline is an agent skill from Sidiora-Labs/centra-gideon-agent. When and how to persist durable memory — save genuine user preferences, facts, and corrections; NEVER persist transient environment failures (a failed command, a flaky network call, a one-off tool error) as lessons; recall before re-asking.

When should I use Memory Discipline?

Memory Discipline fits situations like: AI & LLM Engineering work in your project.

How do I install Memory Discipline in Claude Code?

Run `npx skills add Sidiora-Labs/centra-gideon-agent --skill memory-discipline -a claude-code`. Or copy the skill folder (runtime/gideon/extensions/skills/bundled/memory-discipline in Sidiora-Labs/centra-gideon-agent) into .claude/skills/memory-discipline in your project. Claude Code loads it when a task matches its description.

How do I install Memory Discipline in Codex?

Run `npx skills add Sidiora-Labs/centra-gideon-agent --skill memory-discipline -a codex`. Or copy the skill folder (runtime/gideon/extensions/skills/bundled/memory-discipline in Sidiora-Labs/centra-gideon-agent) into .agents/skills/memory-discipline in your project. Codex loads it when a task matches its description.

Can I use Memory Discipline 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 Sidiora-Labs/centra-gideon-agent --skill memory-discipline -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-discipline, .gemini/skills/memory-discipline, .github/skills/memory-discipline and .opencode/skills/memory-discipline in your project.

What does Memory Discipline need to run?

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

Does Memory Discipline 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 Discipline 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 Discipline use?

Memory Discipline 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 Discipline use?

About 1.1k tokens (SKILL.md is roughly 4.2k 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 Discipline?

Skills that share tags, products or a category with Memory Discipline: Agent Builder (shareAI-lab/learn-claude-code, 78k stars), Add Uint Support (pytorch/pytorch, 104k stars), LLM Benchmarking with lm-evaluation-harness (Orchestra-Research/AI-Research-SKILLs, 13k stars) and Segment Anything Model Guide (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Memory Discipline?

Sidiora-Labs (a GitHub organization) maintains it in Sidiora-Labs/centra-gideon-agent, which has 217 GitHub stars. The repository holds 24 skills in this directory. The repository was last updated on October 8, 2026.

Source: Sidiora-Labs/centra-gideon-agent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.