⏳ This skill is pending AI review.

Scores will appear once the review pipeline completes.

version unknown

sextant

@hellotern⭐ 15 stars

>-

Choose how to use this skill

You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.

1. Native installer

This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.

Do not guess an installer command or replace an existing version without reviewing the diff.

2. Complete package recommended

Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.

No complete ProSkills package is published for this listing yet.

3. Prompt-only

Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.

Need only the instruction file?

Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.

No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.

—/10

// RATINGS

⭐GitHub Stars
⭐⭐ 15 on GitHubGitHub ↗

Growing

🟢ProSkills Score
—
📍

Not yet listed on ClawHub or SkillsMP

// README

Sextant

Architecture-aware engineering principles framework for Claude Code and Codex.

Sextant provides systematic, tiered workflows for the full software engineering lifecycle — bug fixes, new features, refactoring, code review, test writing, requirements refinement, debugging, shipping, sprint planning, migrations, and security audits. Like a nautical sextant that helps navigators fix their exact position before charting a course, it helps the agent understand where it is in the codebase before making changes.


Install

Codex

Codex support is currently documented as a local development integration path, not a published one-command install flow.

The repository root is the plugin root. The Codex manifest lives at .codex-plugin/plugin.json and points to the shared skills/ directory.

For local testing, .agents/plugins/marketplace.json provides a repo-local marketplace entry that points back to this repository. Use it as a development setup reference, not as a published installation contract.

Claude

Option 1: Official Claude marketplace

/plugin install sextant@claude-plugins-official

Or use /plugin to open the interactive plugin manager, navigate to Discover, and search for "sextant".

Option 2: Via GitHub marketplace

/plugin marketplace add hellotern/sextant
/plugin install sextant@mohist-plugins

Option 3: Team configuration

Commit .claude/settings.json to your repository. All team members get sextant automatically on checkout.

{
  "extraKnownMarketplaces": {
    "sextant": {
      "source": {
        "source": "github",
        "repo": "hellotern/sextant"
      }
    }
  },
  "enabledPlugins": {
    "sextant@sextant": true
  }
}

Skills are available immediately — no restart required.

Updating

/plugin update sextant

Cursor

Option 1: Project-level install

Clone the repo and run the installer from your project directory:

git clone https://github.com/hellotern/sextant
cd your-project
python path/to/sextant/.cursor-plugin/install.py

Option 2: Global install (all Cursor projects)

python path/to/sextant/.cursor-plugin/install.py --global

Usage

  • Engineering principles (§0–§6) are automatically active in every Cursor AI interaction.
  • Invoke a workflow via the / command menu in Cursor chat: /sextant-fix-bug, /sextant-add-feature, /sextant-review-code, etc.
  • GitNexus integration activates automatically when .gitnexus/ is present in your project.

Updating

Pull the latest version and re-run the installer:

cd sextant && git pull
python path/to/sextant/.cursor-plugin/install.py

How It Works

For an interactive version of the loading flow diagram, see sextant_loading_flow.html.

flowchart TD
    A(["User prompt"]) --> B

    B["Host matches task type
    to a sextant-* skill"]
    B --> R1["sextant:fix-bug"]
    B --> R2["sextant:add-feature"]
    B --> R3["sextant:modify-feature"]
    B --> R4["sextant:review-code"]
    B --> R5["sextant:write-tests"]
    B --> R6["sextant:refine-requirements"]
    B --> R8["sextant:debug"]
    B --> R9["sextant:ship"]
    B --> R10["sextant:plan"]
    B --> R11["sextant:migrate"]
    B --> R12["sextant:security"]
    B --> R7["sextant (fallback)"]

    R1 --> C
    R2 --> C
    R3 --> C
    R4 --> C
    R5 --> C
    R6 --> C
    R8 --> C
    R9 --> C
    R10 --> C
    R11 --> C
    R12 --> C
    R7 --> F["principles/SKILL.md
    loaded directly as the skill"]

    C["Sub-skill loads via direct include"]
    C --> P["principles/SKILL.md
    §0 · §1 · §2 first (always)
    ── lightweight gate ──
    §3 · §4 · §5 · §6 (medium/large only)"]
    C --> GN["tool-gitnexus/SKILL_BODY.md
    (always included)"]
    P --> D["Task workflow executes"]
    GN --> D
    F --> D

    D --> S1["Light — §0+§1+§2 core path · one-liner output"]
    D --> S2["Medium — +SRP · DRY · contracts"]
    D --> S3["Large — Full SOLID + arch review"]

    classDef skill       fill:#f8fafc,stroke:#cbd5e1,color:#475569
    classDef inject      fill:#dbeafe,stroke:#2563eb,color:#1e40af
    classDef conditional fill:#fef3c7,stroke:#d97706,color:#92400e
    classDef fallback    fill:#f0fdf4,stroke:#86efac,color:#16a34a

    class R1,R2,R3,R4,R5,R6,R7,R8,R9,R10,R11,R12 skill
    class P,D inject
    class GN conditional
    class F fallback

Sextant operates as a layered skill system:

  1. Skill Matching — The host identifies the task type (bug fix, new feature, etc.) and loads the corresponding sextant skill
  2. Direct Injection — Each sub-skill directly includes principles/SKILL_BODY.md at load time via the ! file directive (no bash command required). The file is front-loaded: §0 (baselines), §1 (anti-pattern detection), and §2 (communication) appear first, followed by a lightweight task gate — so short tasks stop reading early without needing a separate file
  3. Scale Assessment — Activates rules proportionally to task size (lightweight / medium / large)
  4. Workflow Execution — Follows the structured workflow, applying only principles relevant to the current task

Task Types

Task TypeSkillKey behavior
Bug Fixsextant:fix-bugDisambiguation gate vs modify-feature; surgical minimal-change fix; progress block + confirmation gate before applying any fix
New Feature / Modulesextant:add-featureFull impact analysis before implementation; TDD contract tests (Large: default Y, Medium: opt-in); progress block + confirmation gate (medium/large)
Modify / Enhance / Refactorsextant:modify-featureDisambiguation gate vs fix-bug; multi-step change strategy; TDD baseline + contract tests (Large: default Y); progress block + confirmation gate (medium/large)
Code Reviewsextant:review-codeDeclares Review-only or Review+patch mode before reading any code; progress block per review dimension
Write Testssextant:write-testsBug-fix entry path for reproduction tests; progress block + confirmation gate (new test modules / full coverage passes)
Requirements Analysis & Refinementsextant:refine-requirementsBreak down ambiguous requirements before coding
Debug (symptom known, location unknown)sextant:debugParadigm-aware bisection; hypothesis limit gate after 3+ eliminations; hands off to fix-bug
Ship / PR Preparationsextant:shipPre-ship checklist; structured PR description; post-merge verification
Sprint Planningsextant:planDependency-ordered task list; transitions to execution pipeline entry after plan confirmation
Migration (multi-module, versioned)sextant:migrateLeaf-first migration sequence; progress block + confirmation gate between phases; legacy cleanup
Security Auditsextant:security4-dimension audit: input validation, auth/authZ, sensitive data, manifest-verifiable dependency checks; progress block per dimension
General Codingsextant (fallback)Lightweight tasks and exempt scenarios

Rule Scaling

ScaleTriggerActive RulesOutput format
LightweightSingle-function adjustments, config changes, style fixes§0 baselines + §1 anti-pattern flags + §2 direct executionOne-liner (✅ / ⚠️)
MediumNew functions/classes, module-internal changes, bug fixes+ §3 task rules + §4 SOLID + §5 DRY/contractsFull summary block
LargeCross-module changes, public interface modifications, new modulesFull §3–§6 activation + architecture auditFull summary block

Interactive Execution Features

Multi-step skills include two interactive behaviors that keep the user in control throughout execution:

Progress tracking — At the start

// HOW IT'S BUILT

KEY FILES

skills/principles/SKILL.mdREADME.md

// REPO STATS

15 stars