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/zevtos/agentpipe/nextgit clone --depth 1 https://github.com/zevtos/agentpipeWhat 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 | $0.00026 | $0.00884 |
| Opus 5 | $0.00013 | $0.00442 |
| Sonnet 5 | $0.00005 | $0.00177 |
| Haiku 4.5 | $0.00003 | $0.00088 |
Grade A, and why
next 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a strategic technical advisor. Your job is to deeply understand the project's current state and make an opinionated recommendation about what to do next. No vague suggestions — give a clear, prioritized action plan.
Context
@CLAUDE.md
Pipeline
Step 1: Full Project Scan — MANDATORY
You MUST use the Agent tool with subagent_type: "Explore" with thoroughness level "very thorough" to perform a comprehensive project analysis.
Prompt for the Explore agent: "Perform a comprehensive analysis of this project's current state. I need to understand:
- What exists — what code is written, what's scaffolded, what's empty/.gitkeep
- What works — are there runnable services, passing tests, working CI?
- Project goals — read ALL documentation, README, CLAUDE.md, specs, ADRs, design docs
- Recent momentum — git log (last 30 commits): what was worked on, when, what direction
- Blockers and debt — TODOs, FIXMEs, failing tests, outdated deps, broken configs
- Infrastructure state — CI/CD, Docker, deployment configs, env setup
- Dependency health — are deps installed? outdated? any security issues?
- Gap analysis — what's documented/planned but not yet implemented?
Be extremely thorough. Read key files, not just list them. I need ground truth, not assumptions."
Wait for the Explore agent to complete before proceeding.
Step 2: Strategic Assessment — MANDATORY
You MUST use the Agent tool with subagent_type: "architect" to get an architectural perspective on priorities.
Prompt for the architect agent: "You are acting as a strategic technical advisor, not just an architect. Based on this project state:
[PASTE FULL EXPLORE AGENT OUTPUT HERE]
Analyze and recommend:
-
Project maturity assessment — where is this project on the spectrum from idea → spec → prototype → MVP → production? Be honest.
-
Critical path analysis — what is the single most important thing to build/fix next? Why? What does it unblock?
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 · 94 lines · 26 tokens per session scan A c80636cbdc3c
next is a command published in the GitHub repository zevtos/agentpipe (11 stars, last pushed 2mo ago), licensed MIT. It adds 26 tokens to every session and 884 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 2026-08-30.
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.
constitution
Create or update the project constitution from interactive or provided principle inputs.
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.