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.
git clone --depth 1 https://github.com/cdeust/ai-architect-mcpWrote 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/cdeust/ai-architect-mcp/run-pipeline)<a href="https://agentmods.dev/commands/cdeust/ai-architect-mcp/run-pipeline"><img src="https://agentmods.dev/badge/commands/cdeust/ai-architect-mcp/run-pipeline/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/cdeust/ai-architect-mcp/run-pipeline"><img src="https://agentmods.dev/badge/commands/cdeust/ai-architect-mcp/run-pipeline.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00017 | $0.00307 |
| Opus 5 | $0.00009 | $0.00153 |
| Sonnet 5 | $0.00003 | $0.00061 |
| Haiku 4.5 | $0.00002 | $0.00031 |
Grade A, and why
run-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 9d 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.
What it actually says
Run Pipeline
Step 1 — Load the orchestrator skill
Read the orchestrator skill instructions:
Read skills/orchestrator/SKILL.md
This file defines the full 11-stage pipeline: health check, discovery, impact analysis, integration design, PRD generation, plan interview, PRD review, implementation, verification, benchmark, deployment, and pull request creation.
Step 2 — Verify MCP server
Call the MCP tools to verify the server is running:
ai_architect_check_context_budget()
ai_architect_load_session_state(session_id="current")
If the MCP server is not reachable, ensure the plugin is installed:
pip install -e mcp/
Step 3 — Execute
Follow the orchestrator SKILL.md instructions exactly:
- Validate blueprint signoff
- Check skill versions
- Load findings queue
- Chain stages 0→10 per finding
- Manage retry loops (Stage 5→4, Stage 7→6)
- Write audit trail at every transition
If $ARGUMENTS is provided, use it as the source for Stage 1 discovery. Otherwise, scan sources/ directory.
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.
- 9d ago First seen · 46 lines · 17 tokens per session scan A 3c80933ac585
run-pipeline is a command published in the GitHub repository cdeust/ai-architect-mcp (1 stars, last pushed 4mo ago), licensed MIT. It adds 17 tokens to every session and 307 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 2026-08-31.
Other commands, from other repositories
release
Create a new release with version bump, changelog update, git tag, npm publish, and optional GitHub Release.
commit
Stage, validate, and commit changes with lint and type checks.
prune
Remove worktrees and local branches whose work has landed.
backfill
Find missing changelog entries from git commits since last tag.
push
Validate and push commits with lint, type, and build checks.
commit-all
Stage and commit all current changes with a single message. Auto Git Push will pick up and push to origin within 30s.