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/plangit 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 | $0.00491 |
| Opus 5 | $0.00013 | $0.00246 |
| Sonnet 5 | $0.00005 | $0.00098 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
plan 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are creating an architecture plan. This is the PLANNING ONLY command — it does NOT implement anything. Use /feature if you want end-to-end development including implementation.
Context
@CLAUDE.md
What to Plan
$ARGUMENTS
Pipeline
Step 1: Design (Architect Agent) — MANDATORY
You MUST use the Agent tool with subagent_type: "architect" to run the architect agent. Do NOT skip this step. Do NOT substitute it with an Explore agent or your own analysis. The architect agent has specialized capabilities for system design.
Prompt for the architect agent: "Plan the implementation of: $ARGUMENTS
Analyze the current codebase thoroughly, then produce:
- Current architecture assessment — what exists, what patterns are used
- Component diagram showing affected modules
- API contract changes (if any endpoints change)
- Data model changes (if schema changes needed)
- Implementation steps in dependency order
- ADR for any significant technical decisions
- Risk assessment with mitigations
- Estimated complexity: SMALL (1-2 files) / MEDIUM (3-5 files) / LARGE (5+ files)"
IMPORTANT: Wait for the architect agent to complete before proceeding. Use its output as the foundation for the plan.
Step 2: Breakout
Break the plan into atomic, committable units:
- Each unit should be independently deployable if possible
- Each unit maps to one conventional commit
- Dependencies between units are explicit
Step 3: Present
## Implementation Plan: $ARGUMENTS
### Architecture Changes
[Diagram and description]
### Implementation Steps
1. [step] — `commit type: description`
2. [step] — `commit type: description`
...
### ADRs
[Any architecture decisions]
### Risks
[What could go wrong]
### Recommendation
- Complexity: [SMALL | MEDIUM | LARGE]
- Suggested approach: [implement directly | use /feature for full pipeline | break into sub-tasks]
Ask: "Plan ready. Want me to implement it? I can use /feature for the full pipeline or start implementing directly."
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 · 65 lines · 26 tokens per session scan A dd11d9a73372
plan 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 491 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.
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.