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/rchgrav/claudebox/context_pipelinegit clone --depth 1 https://github.com/RchGrav/claudeboxWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/rchgrav/claudebox/context_pipeline)<a href="https://agentmods.dev/commands/rchgrav/claudebox/context_pipeline"><img src="https://agentmods.dev/badge/commands/rchgrav/claudebox/context_pipeline.svg" alt="Measured on agentmods" height="20"></a>What 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 5.1 | $0.00000 | $0.01570 |
| Opus 5 | $0.00000 | $0.00785 |
| Sonnet 5 | $0.00000 | $0.00314 |
| Haiku 4.5 | $0.00000 | $0.00157 |
Grade A, and why
context_pipeline 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 6d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
📐 CONTEXT-ENGINEERING PIPELINE (DSPy-Style)
☑️ PURPOSE
Engineer a self-validating, multi-agent software-development workspace that:
- Interviews the user, expands & refines requirements.
- Writes, selects, compresses, and isolates context per the attached Context Engineering Cheat Sheet (Write ▸ Select ▸ Compress ▸ Isolate).
- Scaffolds a project-folder tree populated with
CLAUDE.mdand slash-command files under./.claude/commands/. - Spawns specialists (AutoAgents derivatives) whose prompts are saved in that tree and orchestrated via tmux when available.
- Enforces MetaGPT-style SOP artifact contracts, CAMEL ReAct dialogues, CRITIC gatekeepers, and Self-Refine Reflexion loops until all validation gates pass.
- Emits PRPs (Product-Requirements Prompts): implementation blueprints containing context, docs, tasks, tests, error-handling, and validation commands.
🧩 TOP-LEVEL DSPy PIPELINE
class ContextPipeline(Chain):
"""Declarative overview for Claude Code."""
interview = InterviewStage()
clarify_refine = ClarifyRefineLoop()
scaffold = ProjectScaffold()
generate_prompts = PromptSynthesis()
validation = ValidationGates()
review_loop = ExpertReviewCycle()
finalise = FinaliseArtifacts()
1️⃣ InterviewStage
Ask exactly two opening questions → store replies in runtime_state.overview & runtime_state.gotchas.
| # | Prompt | Store As | Notes |
|---|---|---|---|
| 1 | “Describe what you want to build — be as specific as possible.” | $OVERVIEW |
Must capture functionality & requirements. |
| 2 | “List any gotchas, edge-cases, or things AI assistants often miss.” | $GOTCHAS |
Focus on hidden constraints. |
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.
- 6d ago First seen · 181 lines · 0 tokens per session scan A 2307d0a92d0e
context_pipeline is a command published in the GitHub repository RchGrav/claudebox (1,143 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,570 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
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.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.