Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/shakestzd/contextune/ctx-helpgit clone --depth 1 https://github.com/shakestzd/contextuneWhat 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 | $0.00012 | $0.01994 |
| Opus 5 | $0.00006 | $0.00997 |
| Sonnet 5 | $0.00002 | $0.00399 |
| Haiku 4.5 | $0.00001 | $0.00199 |
Grade A, and why
ctx:help scanned grade A with 0 findings 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 yesterday.
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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contextune Help - Quick Start Guide
Just type naturally—Contextune detects your intent automatically!
✨ Try These Examples (Copy & Paste)
🔍 Fast Research (1-2 min, ~$0.07)
research best React state management library for 2025
→ Spawns 3 parallel agents (web + codebase + deps) → Returns comparison table + recommendation → 67% cost reduction with parallel agents
⚡ Parallel Development (1.5-3x measured speedup)
work on authentication, dashboard, and API in parallel
→ Creates development plan with task breakdown → Sets up git worktrees for parallel execution → Spawns agents to work simultaneously
💡 Feature Discovery
what can Contextune do?
→ Activates intent-recognition skill → Shows all capabilities with examples → Guides you to the right commands
📚 Most Used Commands
/ctx:research <query>
Fast technical research using 3 parallel Haiku agents.
Examples:
/ctx:research best database for user authentication
/ctx:research should I use REST or GraphQL
/ctx:research latest TypeScript testing frameworks
What you get:
- Web research (latest trends, comparisons)
- Codebase analysis (what already exists)
- Dependency check (what's installed vs needed)
- Recommendation with reasoning
Execution: Fast parallel | Cost: ~$0.07
/ctx:status
Monitor progress across all parallel worktrees.
Shows:
- Active worktrees and their branches
- Task completion status
- Git commit history per worktree
- Next steps and blockers
Use when: Working on parallel tasks and want overview
/ctx:configure
Setup guide for persistent status bar integration.
Enables:
- Real-time detection display in status bar
- Zero context overhead (file-based)
- See what Contextune detected without cluttering chat
One-time setup: Adds statusline script to your config
🔧 Advanced Workflow Commands
/ctx:plan
Document development plan for parallel execution.
Creates:
- Modular YAML plan with task breakdown
- Dependency graph (parallel vs sequential tasks)
- Resource allocation strategy
- Time and cost estimates
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.
- yesterday First seen · 326 lines · 12 tokens per session scan A 8defa02defe6
ctx:help is a command published in the GitHub repository shakestzd/contextune (5 stars, last pushed 8mo ago), licensed MIT. It adds 12 tokens to every session and 1,994 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
security-review
CWE 기반 보안 검토 + STRIDE 위협 모델링 (v6 - effort:max 강제).
version
Display current guide and Claude Code versions.
diff-docs
Compare official Anthropic docs baseline vs current snapshot (no network — instant).
docs-review
Phase 4 of documenting-projects: Quality gate with 8 measurable criteria and iteration. Triggers: '/docs-review', invoked by documenting-projects orchestrator.
_registry-protocol
This protocol is MANDATORY for ALL commands, agents, and phases.
memcord-save-progress
Auto-summarize and save conversation progress.