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/deploygit 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 | $0.00022 | $0.00875 |
| Opus 5 | $0.00011 | $0.00438 |
| Sonnet 5 | $0.00004 | $0.00175 |
| Haiku 4.5 | $0.00002 | $0.00088 |
Grade A, and why
deploy 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are orchestrating deployment preparation. This is the final gate before code reaches production. Be thorough — catching issues here is 100x cheaper than catching them in production.
Context
@CLAUDE.md
Auto-context
- Branch: !
git branch --show-current - Status: !
git status --short - Recent commits: !
git log --oneline -10 - Uncommitted changes: !
git diff --stat
Pipeline
Step 1: Pre-flight Checks
Run these checks sequentially, stopping on any failure:
- Clean working tree: No uncommitted changes (warn if found)
- Tests pass: Run the full test suite
- Build succeeds: Run the project build command
- No debug artifacts: Search for
console.log,debugger,binding.pry,import pdb,TODO,FIXME,HACKin changed files since last release tag — warn if found - Environment config: Compare
.env.exampleagainst actual env var usage in code — flag any undocumented variables
Step 2: Security Scan (DevOps Agent)
Run the devops agent:
"Run a deployment security scan:
- Dependency vulnerability scan (npm audit / pip-audit / cargo audit / trivy fs)
- Check for hardcoded secrets (search for API keys, tokens, passwords in source)
- Check Docker image if Dockerfile exists (base image pinned? multi-stage? non-root?)
- Verify security headers are configured (CSP, HSTS, X-Frame-Options)
- Check that production error handling doesn't leak stack traces Report: [PASS / FAIL with findings]"
Step 3: Reviewer Quick Check (Reviewer Agent)
Run the reviewer agent on changes since last release:
"Quick review of all changes since the last release tag.
Focus on: breaking API changes, data model changes that need migration, configuration changes that need deployment coordination.
This is NOT a full code review — just catch deployment-blocking issues."
Step 4: Changelog (Docs Agent)
Run the docs agent:
"Generate a changelog for deployment.
Commits since last tag: !git log $(git describe --tags --abbrev=0 2>/dev/null || echo HEAD~20)..HEAD --oneline
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 · 95 lines · 22 tokens per session scan A 740c27ea9f45
deploy is a command published in the GitHub repository zevtos/agentpipe (11 stars, last pushed 2mo ago), licensed MIT. It adds 22 tokens to every session and 875 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.