Agent skill

Compass Integrity

by chunxiaoxx in chunxiaoxx/nautilus-compass

A skill your agent uses when the user is about to rely on prior session memory for a non-trivial decision, or when something feels off about a recall hit — runs the Merkle chain check, drift…

Custom licenceAuto-check passedAgent Workflows

Install Compass Integrity

skills CLI
$ npx skills add chunxiaoxx/nautilus-compass --skill compass-integrity -a claude-code

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

GitHub CLI
$ gh skill install chunxiaoxx/nautilus-compass compass-integrity --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/chunxiaoxx/nautilus-compass.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/compass-integrity .claude/skills/compass-integrity && 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
compass-integrity
GitHub stars
1.3k
Token cost
~1.3k tokens
SKILL.md length
530 words
Files
1
Skills in repo
2
Repo updated
First seen
Licence
Custom licence

At a glance

A skill your agent uses when the user is about to rely on prior session memory for a non-trivial decision, or when something feels off about a recall hit — runs the Merkle chain check, drift…

  • Works in 5 steps: User says "do we remember", "did we… → User points at a specific memory file or… → Drift incident already suspected ("why… → …
  • The user is about to rely on prior session memory for a non-trivial decision
  • SKILL.md covers Overview, When to invoke, How it works and Decision rules, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Compass Integrity is an agent skill from chunxiaoxx/nautilus-compass. Use when the user is about to rely on prior session memory for a non-trivial decision, or when something feels off about a recall hit — runs the Merkle chain check, drift summary, and daemon liveness in one pass and surfaces any tampering, drift bursts, or daemon-down state before the user acts on stale or corrupted memory.

Its SKILL.md is about 1.3k 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 Agent Workflows, covering Agent memory. It works with Model Context Protocol. The repository describes itself as: Open memory & reliability layer for AI agents + independent judging/verification (NACRE judge, caliber-bench meta-benchmark, preregistered criteria) — by Nautilus Platform.

When your agent uses it

  • The user is about to rely on prior session memory for a non-trivial decision
  • Something feels off about a recall hit — runs the Merkle chain check
  • Daemon liveness in one pass and surfaces any tampering
  • Daemon-down state before the user acts on stale

Example prompts

  • “/compass-integrity”

Workflow steps

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

  1. User says "do we remember", "did we discuss", "based on past sessions" — they're about to lean on memory.
  2. User points at a specific memory file or session ID — verify the chain covers it cleanly.
  3. Drift incident already suspected ("why did the assistant flip on X?", "this looks like a regression") — pull recent drift history.
  4. Session start in a project with memory/, before any recall fires — preflight.
  5. After a crash, conflict resolution, or merge — chain may have been broken by a non-writer edit.

What it can do on your machine

Read from SKILL.md and the folder at commit 32f7e92. 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

Compass Integrity loads about 1.3k tokens when it runs. Until then it costs about 86 tokens; SKILL.md has 530 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~86
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 530 words (~1,274 tokens).

“Compass writes a Merkle hash chain over project memory and a per-session drift signal. Both can be silently broken — a chain mismatch means a memory file was edited outside the writer; a drift-red session means the past assistant output…”

— opening of SKILL.md by chunxiaoxx, Custom licence
name
compass-integrity

Read the full SKILL.md on GitHub

Files

Just SKILL.md in skills/compass-integrity of chunxiaoxx/nautilus-compass.

Open the folder on GitHubat commit 32f7e92

Compare with similar skills

Compass Integrity 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.

Compass Integrity compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Compass Integrity this skillchunxiaoxx/nautilus-compass1.3k—~1.3kAutomated safety check: PassCustom licence
MemPalace Memory SearchMemPalace/mempalace59k—~1.4kAutomated safety check: PassMIT
MemPalace Setup and OperationMemPalace/mempalace59k—~2.2kAutomated safety check: PassMIT
agentmemory Setup and Diagnosticsrohitg00/agentmemory29k—~1kAutomated safety check: NotesApache-2.0
Qmdbreferrari/obsidian-mind4.9k—~1.7kAutomated safety check: PassMIT
Memori MCP Memory UsageMemoriLabs/Memori17k—~3.8kAutomated safety check: PassMIT

Similar skills

  • MemPalace Memory Search

    MemPalace/mempalace

    Mines project files and conversation exports into a local, searchable memory palace and recalls past work by semantic search through the mempalace CLI.

    59k GitHub stars~1.4k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Installs and configures MemPalace as a private local palace, a shared-brain hub or a client of an existing hub, including MCP registration and version-correct initialization.

    59k GitHub stars~2.2k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Sets up and troubleshoots a local agentmemory install, covering the MCP connection, environment variables, ports, authentication and optional feature flags.

    29k GitHub stars~1k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check: notes
  • Qmd

    breferrari/obsidian-mind

    Search the vault using QMD semantic search. An agent skill from breferrari/obsidian-mind.

    4.9k GitHub stars~1.7k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed
  • Memori MCP Memory Usage

    MemoriLabs/Memori

    Teaches an MCP-connected agent when and how to call Memori's recall, summary, compaction, augmentation, feedback and quota tools to keep context across sessions.

    17k GitHub stars~3.8k tokensUpdated 6 days ago
    Agent WorkflowsAuto-check passed
  • Ourmem

    ourmem/omem

    Shared memory that never forgets. An agent skill from ourmem/omem.

    174 GitHub starsUsed in 1 repo~3.4k tokens
    Agent WorkflowsAuto-check passed

More from chunxiaoxx/nautilus-compass

  • Nautilus Compass Memory

    chunxiaoxx/nautilus-compass

    Local-first long-term memory for AI agents via MCP — zero LLM calls at write time, typed retrieval at read time.

    1.3k GitHub stars~1.7k tokensUpdated today
    Auto-check passed

Categories

Questions about Compass Integrity

What does Compass Integrity do?

A skill your agent uses when the user is about to rely on prior session memory for a non-trivial decision, or when something feels off about a recall hit — runs the Merkle chain check, drift…. Compass Integrity is an agent skill from chunxiaoxx/nautilus-compass. Use when the user is about to rely on prior session memory for a non-trivial decision, or when something feels off about a recall hit — runs the Merkle chain check, drift summary, and daemon liveness in one pass and surfaces any tampering, drift bursts, or daemon-down state before the user acts on stale or corrupted memory.

When should I use Compass Integrity?

Compass Integrity fits situations like: the user is about to rely on prior session memory for a non-trivial decision; something feels off about a recall hit — runs the Merkle chain check; daemon liveness in one pass and surfaces any tampering; daemon-down state before the user acts on stale.

How do I install Compass Integrity in Claude Code?

Run `npx skills add chunxiaoxx/nautilus-compass --skill compass-integrity -a claude-code`. Or copy the skill folder (skills/compass-integrity in chunxiaoxx/nautilus-compass) into .claude/skills/compass-integrity in your project. Claude Code loads it when a task matches its description.

How do I install Compass Integrity in Codex?

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

Can I use Compass Integrity 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 chunxiaoxx/nautilus-compass --skill compass-integrity -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/compass-integrity, .gemini/skills/compass-integrity, .github/skills/compass-integrity and .opencode/skills/compass-integrity in your project.

What does Compass Integrity need to run?

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

Does Compass Integrity 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 Compass Integrity 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 Compass Integrity use?

Compass Integrity has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Compass Integrity use?

About 1.3k tokens (SKILL.md is roughly 5.1k 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 Compass Integrity?

Skills that share tags, products or a category with Compass Integrity: MemPalace Memory Search (MemPalace/mempalace, 59k stars), MemPalace Setup and Operation (MemPalace/mempalace, 59k stars), agentmemory Setup and Diagnostics (rohitg00/agentmemory, 29k stars) and Qmd (breferrari/obsidian-mind, 4.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Compass Integrity?

chunxiaoxx (a GitHub user) maintains it in chunxiaoxx/nautilus-compass, which has 1,255 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 8, 2026.

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