A cleanup workflow for removing Almanac and CodeAlmanac command-line tools and their related local files. It is intended to return the machine to the state of a first-time Almanac installation.

Use it to check for and uninstall Almanac tools, remove their npm installations and caches, and clean up related configuration and hook files.

It helps remove old installations, caches, configuration files, and editor hooks without affecting unrelated files, packages, or integrations.

How AlmanacCode/codealmanac configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to AlmanacCode/codealmanac. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/AlmanacCode/codealmanac/main/.agents/skills/cleanslate/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/AlmanacCode/codealmanac

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/almanaccode/codealmanac/cleanslate/github.svg)](https://agentmods.dev/skills/almanaccode/codealmanac/cleanslate)

Your own site

<a href="https://agentmods.dev/skills/almanaccode/codealmanac/cleanslate"><img src="https://agentmods.dev/badge/skills/almanaccode/codealmanac/cleanslate/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/almanaccode/codealmanac/cleanslate"><img src="https://agentmods.dev/badge/skills/almanaccode/codealmanac/cleanslate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 946 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 2 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

high Agent Snooping · line 37
Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.

Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
medium MCP Rug Pull · line 59
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Fix: Pin the version: npx @scope/[email protected]

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00047	$0.00946
Opus 5.5	$0.00019	$0.00378
Sonnet 5.5	$0.00009	$0.00189
Haiku 4.5	$0.00005	$0.00095

Measured 2mo ago against content hash 7b6663d46d93, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

cleanslate scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- In `~/.claude/settings.json`, remove only hook commands whose command path ends with `almanac-capture.sh`; preserve every foreign hook.

.agents/skills/cleanslate/SKILL.md · 60 lines

What it actually says

Almanac Clean Slate

Reset this machine to a first-time Almanac user state, then report exactly what changed.

Goal: remove every installed or cached codealmanac/Almanac CLI artifact from this laptop without touching unrelated user files, unrelated npm packages, or foreign editor hooks.

Work from safest to most direct:

Record the starting state:
- command -v almanac alm codealmanac || true
- npm list -g codealmanac --depth=0 || true
- find ~/.npm/_npx -path '*/node_modules/codealmanac/package.json' -print 2>/dev/null || true
- Check for ~/.almanac, ~/.claude/almanac.md, ~/.claude/almanac-reference.md, legacy ~/.claude/codealmanac*.md, ~/.claude/hooks/almanac-capture.sh, ~/.codex/hooks.json, and ~/.cursor/hooks.json.
If any Almanac CLI command exists, run the product uninstaller first:
- Prefer almanac uninstall --yes.
- If almanac is missing but codealmanac exists, run codealmanac uninstall --yes.
- If both fail, continue with manual cleanup.
Remove npm/global installs and caches:
- Run npm uninstall -g codealmanac || true.
- Remove codealmanac package directories under all local nvm global roots if they still exist.
- Remove global bin shims named almanac, alm, and codealmanac only when they point at a codealmanac install.
- Remove each ~/.npm/_npx/<hash> directory whose node_modules/codealmanac/package.json exists.
Remove Almanac home/config artifacts:
- Remove ~/.almanac.
- Remove ~/.claude/almanac.md, ~/.claude/almanac-reference.md, ~/.claude/codealmanac.md, and ~/.claude/codealmanac-reference.md.
- Remove ~/.claude/hooks/almanac-capture.sh if it exists.
Clean editor hook settings safely:
- In ~/.claude/settings.json, remove only hook commands whose command path ends with almanac-capture.sh; preserve every foreign hook.
- In ~/.codex/hooks.json, remove only hook commands whose command path ends with almanac-capture.sh; preserve every foreign hook.
- In ~/.cursor/hooks.json, remove only hook commands whose command path ends with almanac-capture.sh; preserve every foreign hook.
- If a hook container becomes empty after removing Almanac's command, remove that empty container/key.
Clean Claude imports safely:
- In ~/.claude/CLAUDE.md, remove lines that are exactly @~/.claude/almanac.md or @~/.claude/codealmanac.md, plus those same lines followed by spaces/tabs and annotations.
- Preserve lines that merely mention those paths inside other prose.
- If CLAUDE.md becomes empty after removing Almanac imports, remove it.
Verify the clean slate:
- hash -r || true
- command -v almanac alm codealmanac || true
- npm list -g codealmanac --depth=0 || true
- find ~/.npm/_npx -path '*/node_modules/codealmanac/package.json' -print 2>/dev/null || true
- Check that ~/.almanac, guide files, and almanac-capture.sh are gone.
- Check that no hook command ending in almanac-capture.sh remains in Claude, Codex, or Cursor hook settings.

Output:

Show the exact commands/actions you ran in order.
Mark each as removed, already absent, or skipped with the reason.
End with the remaining command -v and npm/global/npx verification output.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 60 lines · 47 tokens per session scan B 7b6663d46d93

Subscribe to this mod's changes

cleanslate is a skill published in the GitHub repository AlmanacCode/codealmanac (994 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 47 tokens to every session and 946 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

ai claude cli codebase codex coding-agents

brain-ingest

The process for digesting a conversation, document, or research result, classifying it, and writing it down as brain content (a root-page update or a new/updated page) through the brain CLI.

mindmuxai/brain.md · 48 tokens

gate-control

Canonical VideoStudio review authorization and state-transition policy. Use after any Gate B/C/Preview/D decision, post-gate revision, resumed approval, or exhausted visual-QA result across COMPOSE/AUTO/GENERATE/EDIT; maps explicit user authority and durable artifact state to one next action with ovs gate transition.…

Orkas-AI/Orkas-VideoStudio · 81 tokens

stage-edit

Intelligent editing of real user-supplied footage—understand it with transcript/inspected-frame/scene/silence/quality evidence, then choose deterministic timeline operations or a constrained semantic AI edit. Trigger for repurpose, montage, cleanup, localization, narration, or local content changes.

Orkas-AI/Orkas-VideoStudio · 62 tokens

orchestration

The master program for producing or editing a video end to end — read this at the START of any video task (after video-router), then follow the gates and the per-line steps. Trigger for "make / edit / cut / caption / dub / animate a video"; it sequences the compose / generate / edit lines and the approval gates. Do…

Orkas-AI/Orkas-VideoStudio · 99 tokens

stage-assemble

Deterministically assemble an approved cross-modal EDL (plan.json) into a finished video — produce each segment (edit/compose/generate/provided, delegated to its line), then assemble in ffmpeg tiers: concat primaries → overlay composed layers → mix narration once (coverage check) → burn captions → verify loudness…

Orkas-AI/Orkas-VideoStudio · 0 tokens

research

Use when the user asks you to research, compare, fact-check or find current information, and the answer should come with sources.

katipally/openlive · 28 tokens

codealmanac: Skill for Claude Code