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-mcp-codebaseWrote 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-codebase/estimate)<a href="https://agentmods.dev/commands/cdeust/ai-architect-mcp-codebase/estimate"><img src="https://agentmods.dev/badge/commands/cdeust/ai-architect-mcp-codebase/estimate/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-codebase/estimate"><img src="https://agentmods.dev/badge/commands/cdeust/ai-architect-mcp-codebase/estimate.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 | $0.00000 | $0.00180 |
| Opus 5.5 | $0.00000 | $0.00072 |
| Sonnet 5.5 | $0.00000 | $0.00036 |
| Haiku 4.5 | $0.00000 | $0.00018 |
Grade A, and why
estimate 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 1mo 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
Quick Estimate
Fast Fermi bracket for a question. Produces an order-of-magnitude bound in under 2 minutes.
Instructions
-
Take the question from $ARGUMENTS. If no units given, ask for units.
-
Decompose into 3-5 bracketable factors. State the source or reasoning for each bound.
-
Multiply to get the bracket [low, high].
-
Name the dominant uncertainty (the widest factor).
-
Cross-check with one independent decomposition. If they disagree by >10x, flag it.
-
Present:
Quick Estimate: [question] Bracket: [low] to [high] Dominant uncertainty: [factor] Cross-check: [agrees/disagrees to x?] -
Do NOT produce false precision. Brackets only.
$ARGUMENTS
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.
- 1mo ago First seen · 28 lines · 0 tokens per session scan A 05bbd7e0a100
estimate is a command published in the GitHub repository cdeust/ai-architect-mcp-codebase (7 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 180 tokens. 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
genesis
Initialize cortex vault — set up config, vault structure, and rebuild index.
converge
Run an unattended review→fix→re-review loop on the current branch until the reviewer has no findings at or above Medium, then push once. Findings stay in a local scratch file and are never posted to GitHub. Stops early on oscillation, a red test suite, or a 4-review cap.
debug
Diagnose a bug, failing test, or unexpected behavior — root-cause first, minimal fix, regression test. Performance-shaped symptoms (slow, latency, profiling) are routed to workflow-performance-investigation via one clarifying question.
handoff
Hand work to Claude Code or Pi through a bounded semantic checkpoint, resume or recover a checkpoint, inspect status, or close a completed handoff.
test
Invoke the test-writer subagent to add focused, behavioural tests in the target language's idiom. Pass --mode e2e (or --e2e) to run the browser-driven E2E pipeline instead, or --mode e2e-live for an ephemeral, human-watched browser walkthrough with no spec file written.
memory
Record a cross-harness memory entry (correction, gotcha, or project fact) into the current harness's per-repo memory store.