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/penwyp/claudepreference/m-next-contextgit clone --depth 1 https://github.com/penwyp/ClaudePreferenceWhat 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 | $0.00000 | $0.00723 |
| Opus 5 | $0.00000 | $0.00362 |
| Sonnet 5 | $0.00000 | $0.00145 |
| Haiku 4.5 | $0.00000 | $0.00072 |
Grade A, and why
m-next-context 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 2d 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.
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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Next Context Workflow: Compile Task List & Background Info
Target: $ARGUMENTS (Default: unstaged code changes and current conversation context)
Scope: Analyze project state and compile comprehensive task context
Execution Steps
-
Project Background Analysis
- Inspect unstaged code changes and modifications
- Extract context from current conversation history
- Assess project objectives and technical constraints
-
Task Extraction & Classification
- Detect TODO markers and incomplete implementations
- Identify open issues and planned features
- Classify tasks by type (feature, bugfix, refactor, documentation)
-
Supporting Material Collection
- Gather relevant file paths and documentation
- Identify external links and reference materials
- Map resources to specific tasks and requirements
-
Ambiguity Detection
- Identify unclear requirements and specifications
- Flag missing information and decision points
- Generate clarifying questions for resolution
-
Context Compilation
- Synthesize project state narrative
- Organize tasks with clear relationships
- Structure references for easy access
-
Generate Context Report
- Compile findings into structured markdown format
- Save to
docs/workspaces/next-context-MM-dd-HH-mm-ss.md
Output Format
English Report
context
- Concise background narrative describing current project state
- Key objectives and development goals
- Technical constraints and architectural decisions
- Recent progress and conversation highlights
tasks
Array of task objects with structure:
{
"id": "string",
"description": "string",
"type": "feature|bugfix|refactor|docs|test",
"status": "pending|in-progress|blocked|ready"
}
references
- File paths relevant to each task
- Documentation and specification links
- External resources and dependencies
- Related discussions and decision records
clarifications
Array of questions for ambiguities requiring resolution:
- Unclear requirements or scope boundaries
- Missing technical specifications
- Implementation approach uncertainties
- Resource and timeline considerations
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.
- 2d ago First seen · 111 lines · 0 tokens per session scan A 5d5d11dbd1f2
m-next-context is a command published in the GitHub repository penwyp/ClaudePreference (137 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 723 tokens. 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 2026-08-30.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.