CtrlK
BlogDocsLog inGet started
Tessl Logo

codex-settings-sync

Use when the user wants to migrate Codex state in ~/.codex into Agent Filesystem and mount the same shared Codex memory/settings across multiple computers. Recommends a .afsignore before migration and defaults to excluding worktrees, caches, logs, and temporary files.

96

1.61x
Quality

Does it follow best practices?

Impact

100%

1.61x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

87%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is lean and highly actionable with concrete commands and a clear workflow, and it makes appropriate use of a single bundled reference. Its main gap is the absence of explicit validation/feedback checkpoints for destructive migration steps.

Suggestions

Add an explicit validation checkpoint before destructive steps — e.g., verify a ~/.codex.local-backup exists after moving the original aside, and abort the import if it does not.

Introduce a validate-fix-retry loop around './afs status' on each machine (e.g., if the mount is not live, re-run './afs config set --mode mount' before retrying './afs ws mount') to satisfy the destructive-operation feedback-loop expectation.

Surface a guardrail earlier in the workflow that no two machines should mount the shared ~/.codex simultaneously, rather than only in the trailing notes.

DimensionReasoningScore

Conciseness

Lean body that assumes Claude's competence — defaults, a numbered workflow, notes, and rollback with no padded explanations of concepts Claude already knows; every section earns its place.

3 / 3

Actionability

Provides copy-paste-ready executable commands such as './afs ws import --mount-at-source .codex ~/.codex', './afs ws mount .codex ~/.codex', './afs config set --mode mount', and concrete rollback commands.

3 / 3

Workflow Clarity

An 8-step sequence with a final verification step exists, but the migration moves/replaces ~/.codex (destructive) and lacks explicit validation checkpoints or a validate-fix-retry feedback loop between destructive steps, capping this at 2 per the destructive-operations guideline.

2 / 3

Progressive Disclosure

Well under 50 lines with cleanly organized sections and a single well-signaled, real one-level reference to assets/.afsignore; no nested or deep reference chains.

3 / 3

Total

11

/

12

Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is concise, third-person, and explicitly covers both capability and trigger conditions with concrete actions. It is clearly distinguishable and free of fluff or over-claims.

DimensionReasoningScore

Specificity

Names multiple concrete actions — 'migrate Codex state in ~/.codex into Agent Filesystem', 'mount the same shared Codex memory/settings across multiple computers', and specific default exclusions (worktrees, caches, logs, temporary files).

3 / 3

Completeness

Explicitly answers both what (migrate ~/.codex into Agent Filesystem and mount shared settings) and when via the 'Use when the user wants to...' trigger clause.

3 / 3

Trigger Term Quality

Uses natural phrasing a user would say — 'migrate Codex state', 'shared Codex memory/settings', 'across multiple computers' — with good coverage rather than opaque jargon.

3 / 3

Distinctiveness Conflict Risk

Targets a clear niche — syncing Codex state via Agent Filesystem across machines — with triggers unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
redis/agent-filesystem
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.