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/featuregit 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 | $0.00029 | $0.00880 |
| Opus 5 | $0.00015 | $0.00440 |
| Sonnet 5 | $0.00006 | $0.00176 |
| Haiku 4.5 | $0.00003 | $0.00088 |
Grade A, and why
feature 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are orchestrating end-to-end feature development. Follow this pipeline step by step. Each stage gates the next — do not proceed if a stage produces GATE: FAIL.
Context
@CLAUDE.md
Feature Request
$ARGUMENTS
Pipeline
Step 1: Specification (PM Agent)
Run the pm agent:
"Feature request: $ARGUMENTS
Read the existing codebase to understand context, then create a feature specification:
- User stories with acceptance criteria
- Edge cases and error scenarios
- Non-functional requirements with specific targets
- Impact on existing features
- Out of scope
- Open questions"
Present to user. Ask: "Does this capture the feature correctly? Any adjustments?" Wait for confirmation before proceeding.
Step 2: Design (Architect Agent)
Run the architect agent:
"Based on this feature specification:
[paste PM output]
Read the existing codebase architecture, then design this feature:
- Which existing components are affected?
- New components/modules needed
- API changes (new endpoints, modified contracts)
- Data model changes (new tables, altered columns, new indexes)
- Integration points
- ADR if a significant technical decision is required
- Implementation plan: ordered list of changes to make"
Present to user. Ask: "Good approach? Any concerns?" Wait for confirmation.
Step 3: Database Changes (DBA Agent — if needed)
ONLY if the architect identified data model changes, run the dba agent:
"Based on this design:
[paste relevant data model changes from architect output]
Read the existing schema, then:
- Design the migration with expand-contract pattern if breaking changes
- Provide exact SQL with safety measures (lock_timeout, CONCURRENTLY, NOT VALID)
- Specify rollback plan
- Identify index changes needed"
Step 4: Implementation
Implement the feature following the architect's plan:
- Follow the ordered implementation steps from the design
- Apply the database migration from the DBA output if applicable
- Write the code following project conventions
- Add input validation and error handling
- Add structured logging for new operations
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 · 117 lines · 29 tokens per session scan A 2d38a2c5f467
feature is a command published in the GitHub repository zevtos/agentpipe (11 stars, last pushed 2mo ago), licensed MIT. It adds 29 tokens to every session and 880 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.