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

Codex Fluent

by majiayu000 in majiayu000/spellbook

A skill your agent uses when Codex feels slow, bloated, or heavy after heavy use.

MITAuto-check passed

Install Codex Fluent

skills CLI
$ npx skills add majiayu000/spellbook --skill codex-fluent -a claude-code

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

GitHub CLI
$ gh skill install majiayu000/spellbook codex-fluent --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/majiayu000/spellbook.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/codex-fluent .claude/skills/codex-fluent && 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
codex-fluent
GitHub stars
287
Token cost
~1.4k tokens
SKILL.md length
693 words
Files
5 (incl. references)
Skills in repo
97
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when Codex feels slow, bloated, or heavy after heavy use.

  • Works in 5 steps: Diagnosis (Report Mode) → Handoff Creation (Mandatory for Valuable… → Apply Maintenance → …
  • Codex feels slow
  • SKILL.md covers Core Philosophy, When to Use This Skill, Safety Rules (Hard) and Recommended Cadence, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Codex Fluent is an agent skill from majiayu000/spellbook. Use when Codex feels slow, bloated, or heavy after heavy use. Provides safe session hygiene, archive strategy, and handoff discipline to keep daily Codex usage responsive and low-friction. Always pairs with comprehensive handoffs before archiving active work.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `references/examples/handoff-quality-example.md`, `references/examples/typical-before-after.md` and `references/handoff-template.md`).

The repository describes itself as: Cross-runtime skills for Claude Code, Codex, and multi-agent workflows. The licence is MIT.

When your agent uses it

  • Codex feels slow
  • Heavy after heavy use

Example prompts

  • “/codex-fluent”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Diagnosis (Report Mode)
  2. Handoff Creation (Mandatory for Valuable Work)
  3. Apply Maintenance
  4. Verification
  5. (Optional) Recurring Reminder

What it can do on your machine

Read from SKILL.md and the folder at commit ed52af7. 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

Codex Fluent loads about 1.4k tokens when it runs, and up to ~3.5k if it reads all its reference files. Until then it costs about 68 tokens; SKILL.md has 693 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~68
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.5k

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 majiayu000/spellbook at commit ed52af7, republished under its MIT licence (© majiayu000). 693 words, ~1,449 tokens.

Download SKILL.mdSave it as .claude/skills/codex-fluent/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
codex-fluent
description
Use when Codex feels slow, bloated, or heavy after heavy use. Provides safe session hygiene, archive strategy, and handoff discipline to keep daily Codex usage responsive and low-friction. Always pairs with comprehensive handoffs before archiving active work.

Codex Fluent

Keep Codex feeling fast, light, and pleasant to use over months of heavy daily work.

This skill is about operational fluency — the subjective experience of Codex staying responsive, starting quickly, and not forcing you to fight accumulated context and state.

Core Philosophy

  • Fresh small state = speed and low mental load.
  • Old work must be preserved, but moved out of the active path.
  • Handoffs are non-negotiable before archiving anything you might still need.
  • Never delete. Archive with clear restore paths.

When to Use This Skill

  • Codex feels laggy on startup or when switching sessions.
  • You have many long-running or old chats you rarely touch but don't want to lose.
  • Before big maintenance or after noticing session directory growth.
  • After a codex-retrospective session where Codex itself flagged repeated context bloat or "I keep having to re-explain the current state".

Safety Rules (Hard)

  1. Inspect first, always. The first invocation must be report-only.
  2. Handoff before archive. For any active repo chat you might continue, a high-quality handoff document + reactivation prompt must exist before it is moved to archive.
  3. Backup before mutate. All changes must be preceded by a timestamped backup.
  4. Archive, never delete. Sessions, logs, and worktrees are moved to dedicated archive directories (~/.codex/archived_sessions/, archived_worktrees/, archived_logs/).
  5. Codex must be closed (or you explicitly accept --wait-for-codex-exit) before any filesystem changes to active state.
  6. Never touch credentials, global skills you still use, or memory files without explicit confirmation.
  • Heavy daily multi-repo users: weekly report + maintenance when needed.
  • Moderate users: every 10–14 days.
  • The skill can generate a recurring report-only reminder prompt for you.

Workflow

1. Diagnosis (Report Mode)

Ask:

Use codex-fluent to inspect my current Codex local state and give me a clear picture of what is causing drag.

The skill will report on:

  • Active vs archived session sizes
  • Largest active sessions and their ages
  • Stale worktrees
  • Large log files
  • Potential thread metadata bloat (title/preview)
  • Dead config entries
  • Heavy background processes (reported only)
2. Handoff Creation (Mandatory for Valuable Work)

Before any archiving of chats you care about, create excellent handoffs.

Use the template in references/handoff-template.md.

The reactivation prompt must allow a completely fresh Codex thread (or even Claude via the codex skill) to pick up without the old giant context.

3. Apply Maintenance

Only after handoffs exist for everything important:

Use codex-fluent to perform safe maintenance now. I have created handoffs for the sessions I want to keep continuity on. Codex is closed.

What a normal apply does:

  • Timestamped backup to ~/Documents/Codex/codex-backups/codex-fluent-YYYYMMDD-HHMM/
  • Move qualifying old sessions to ~/.codex/archived_sessions/
  • Move stale worktrees to ~/.codex/archived_worktrees/
  • Rotate oversized logs
  • Clean dead project entries from config
  • Normalize certain path issues where safe
4. Verification

Run diagnosis again and compare before/after sizes and feel.

Show full SKILL.md (282 more words)Show less
5. (Optional) Recurring Reminder

Generate a safe, report-only weekly reminder prompt that never applies changes automatically.

Integration with Other Spellbook Skills

  • After running codex-retrospective, if Codex complains about "having to re-read huge context every time" or repeated state loss, this skill is the natural follow-up.
  • Design handoff documents as the compact representation of a thread: preserve the objective, constraints, decisions, verification, and unresolved work.
  • Handoff documents created here are excellent material to feed into future codex-retrospective runs.

What This Skill Will Not Do

  • Automatically delete anything.
  • Kill processes.
  • Touch credentials or irreplaceable memory.
  • Archive pinned or explicitly marked "do not touch" sessions without confirmation.
  • Promise universal speedups (results depend on your usage patterns).

Gotchas

  • A large session is not automatically safe to archive. If the work is active, blocked, or likely to resume, create the handoff first and verify that the reactivation prompt points to a real file.
  • Reported size reductions do not prove product speedups by themselves. Compare before/after active-state size and a fresh startup or session-switch test.
  • Never treat "Codex is closed" as an assumption. If apply mode would touch active state, verify process state or get explicit user acceptance first.
  • Do not normalize paths, prune config, or move global skills in the same pass as session archiving unless the diagnosis explicitly named those candidates.

References

  • references/handoff-template.md — High-quality handoff document template + reactivation prompt
  • references/maintenance-checklist.md — Step-by-step safe maintenance checklist
  • references/examples/ — Real-world (anonymized) before/after reports and handoff examples

Success Criteria

After using this skill properly you should experience:

  • Noticeably faster Codex startup and session switching
  • Lower anxiety about "losing history"
  • Clear, searchable handoff documents in your important repos
  • A repeatable, low-risk maintenance habit

Start with a diagnosis run. The rest follows naturally.

© majiayu000, 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 4 other files (references) in skills/codex-fluent of majiayu000/spellbook.

  • SKILL.md
  • references/examples/handoff-quality-example.md
  • references/examples/typical-before-after.md
  • references/handoff-template.md
  • references/maintenance-checklist.md

Open the folder on GitHubat commit ed52af7

Compare with similar skills

Codex Fluent 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.

Codex Fluent compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Codex Fluent this skillmajiayu000/spellbook287—~1.4kAutomated safety check: PassMIT
Make Interfaces Feel Betteraffaan-m/ECC276k1 repos~1.2kAutomated safety check: PassMIT
Profiling Slow API EndpointsPostHog/posthog40k—~1kAutomated safety check: PassCustom licence
Slow TestsUKGovernmentBEIS/inspect_ai3k—~1.4kAutomated safety check: PassMIT
Make Interfaces Feel Bettersamuelclay/NewsBlur7.6k10 repos~1.5kAutomated safety check: PassMIT
FeelSoul-Brews-Studio/arra-oracle-skills-cli123—~1.1kAutomated safety check: PassMIT

Similar skills

  • Make Interfaces Feel Better

    affaan-m/ECC

    Apply concrete design-engineering details that make interfaces feel polished.

    276k GitHub starsUsed in 1 repo~1.2k tokens
    Frontend & DesignAuto-check passed

  • Profiling Slow API Endpoints

    PostHog/posthog

    Official

    Profiles slow PostHog API endpoints when the main cost is in Postgres or Python.

    40k GitHub stars~1k tokensUpdated today
    DatabasesAuto-check passed

  • Slow Tests

    UKGovernmentBEIS/inspect_ai

    Run the gated test classes that plain pytest skips (slow Docker/sandbox tests, live model-provider API tests, flaky tests, trio variants).

    3k GitHub stars~1.4k tokensUpdated today
    Testing & QAAuto-check passed

  • Make Interfaces Feel Better

    samuelclay/NewsBlur

    Design engineering principles for making interfaces feel polished.

    7.6k GitHub starsUsed in 10 repos~1.5k tokens
    Frontend & DesignAuto-check passed

  • Feel

    Soul-Brews-Studio/arra-oracle-skills-cli

    Capture how the system feels — energy, momentum, burnout, breakthrough.

    123 GitHub stars~1.1k tokensUpdated 7 days ago
    Auto-check passed

  • Interfaces That Feel

    Owl-Listener/designer-skills

    Apply an emotional resonance lens to a UI that is technically correct but flat, prescribing changes at the copy, motion, and interaction layer.

    2.9k GitHub starsUsed in 1 repo~977 tokens
    Frontend & DesignAuto-check passed

More from majiayu000/spellbook

All 97 skills in this repo

  • Skill Ecosystem Doctor

    majiayu000/spellbook

    Audits and repairs how coding-agent Skills are owned, copied and exposed across runtimes, from canonical sources to quarantine and retirement.

    287 GitHub stars~3k tokensUpdated yesterday
    Auto-check passed

  • AGENTS.md Scaffold

    majiayu000/spellbook

    Scans a repository for real evidence and proposes, or on request writes, a small stack of root and scoped AGENTS.md files with validation commands and generated-file boundaries.

    287 GitHub stars~1.5k tokensUpdated yesterday
    Auto-check passed

  • Product Demo Builder

    majiayu000/spellbook

    Plans, produces or diagnoses evidence-backed product demo videos: script, capture plan, pacing checks and verified final media built on real product behavior.

    287 GitHub stars~3.3k tokensUpdated yesterday
    Auto-check passed

  • Flowguard Task Guard

    majiayu000/spellbook

    Single entry point that routes long or ambiguous agent tasks, checks live state, bounds autonomous loops and leaves a resumable handoff.

    287 GitHub stars~2.1k tokensUpdated yesterday
    Auto-check passed

  • npm Supply Chain Check

    majiayu000/spellbook

    Scans a repository, its lockfiles and node_modules for known malicious npm package versions and install-time indicators, using a read-only Python scanner.

    287 GitHub stars~1.5k tokensUpdated yesterday
    Auto-check passed

  • Product Manager Toolkit

    majiayu000/spellbook

    Product management helpers: a RICE scoring script, an interview transcript analyzer and PRD templates for prioritizing features, synthesizing research and writing requirements.

    287 GitHub stars~2.2k tokensUpdated yesterday
    Auto-check passed

Questions about Codex Fluent

What does Codex Fluent do?

A skill your agent uses when Codex feels slow, bloated, or heavy after heavy use. Codex Fluent is an agent skill from majiayu000/spellbook. Use when Codex feels slow, bloated, or heavy after heavy use.

When should I use Codex Fluent?

Codex Fluent fits situations like: Codex feels slow; heavy after heavy use.

How do I install Codex Fluent in Claude Code?

Run `npx skills add majiayu000/spellbook --skill codex-fluent -a claude-code`. Or copy the skill folder (skills/codex-fluent in majiayu000/spellbook) into .claude/skills/codex-fluent in your project. Claude Code loads it when a task matches its description.

How do I install Codex Fluent in Codex?

Run `npx skills add majiayu000/spellbook --skill codex-fluent -a codex`. Or copy the skill folder (skills/codex-fluent in majiayu000/spellbook) into .agents/skills/codex-fluent in your project. Codex loads it when a task matches its description.

Can I use Codex Fluent 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 majiayu000/spellbook --skill codex-fluent -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/codex-fluent, .gemini/skills/codex-fluent, .github/skills/codex-fluent and .opencode/skills/codex-fluent in your project.

What does Codex Fluent need to run?

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

Does Codex Fluent 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 Codex Fluent 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 Codex Fluent use?

Codex Fluent is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Codex Fluent use?

About 1.4k tokens (SKILL.md is roughly 5.8k 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 2k tokens, read only when the agent opens those files.

What are the alternatives to Codex Fluent?

Skills that share tags, products or a category with Codex Fluent: Make Interfaces Feel Better (affaan-m/ECC, 276k stars), Profiling Slow API Endpoints (PostHog/posthog, 40k stars), Slow Tests (UKGovernmentBEIS/inspect_ai, 3k stars) and Make Interfaces Feel Better (samuelclay/NewsBlur, 7.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Codex Fluent?

majiayu000 (a GitHub user) maintains it in majiayu000/spellbook, which has 287 GitHub stars. The repository holds 97 skills in this directory. The repository was last updated on October 8, 2026.

Source: majiayu000/spellbook on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.