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/odere-pro/claude-aws-architectWrote 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/odere-pro/claude-aws-architect/aws-kb)<a href="https://agentmods.dev/commands/odere-pro/claude-aws-architect/aws-kb"><img src="https://agentmods.dev/badge/commands/odere-pro/claude-aws-architect/aws-kb/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/odere-pro/claude-aws-architect/aws-kb"><img src="https://agentmods.dev/badge/commands/odere-pro/claude-aws-architect/aws-kb.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 | $0.00040 | $0.00669 |
| Opus 5 | $0.00020 | $0.00334 |
| Sonnet 5 | $0.00008 | $0.00134 |
| Haiku 4.5 | $0.00004 | $0.00067 |
Grade A, and why
aws-kb 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 8d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are invoking the claude-aws-architect kb-navigator for a read-only AWS knowledge lookup, CLI reference query, comparison, onboarding pointer, or "what should I learn next" recommendation.
Inputs
- User query:
$ARGUMENTS - Per-feature directory (read-only, only if continuing an existing feature for ledger reuse):
.claude/specs/<feature>/ - MCP server used:
kb(aws-knowledge), as configured by.mcp.jsonat the plugin root.
Action
Delegate to the claude-aws-architect-kb-navigator-agent subagent. The subagent owns:
- Intent classification across
lookup,cli,compare,onboard,next,region-qperreferences/intents.mdin theaws-kb-navigatorskill. - Narrow-tool selection on the
kbMCP server viaaws-mcp-routingand the per-turn 6-call budget. - Cache pre-check and ledger persistence via
aws-grounding-cache(durable side effect; no spec-artefact writes). - Response assembly under the five-section template enforced by
aws-kb-response: Answer → bullets-or-block → Citations → Related → Next. - Degraded-marker propagation (
grounding-deferred,budget-exhausted,redaction-failed) verbatim to the caller.
Boundaries
- This command does not bypass the kb-navigator: never call MCP servers or sibling specialists directly from the command body.
- This command never writes to
.claude/specs/<feature>/other than the grounding-ledger append owned by the cache skill, and never creates a feature directory. - This command short-circuits when the query names an SDLC artefact (
requirements,design,tasks,runbook,threat-model,ROM) or a verb-of-creation; the kb-navigator will redirect the caller to/awsrather than mixing modes.
Intent flags
--cli <service>— AWS CLI reference lookup; surfacesaws <service> <verb>reference and an optional SOP recipe.--compare <a> vs <b>— side-by-side comparison on a stated dimension.--onboard <topic>— onboarding pointer for a service or learning track around a topic.--next— recommendations tied to the most recent grounding-ledger entry.--deep— lift the default 250-word ceiling to 600 words.- (no flag) — general
lookupintent.
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.
- 8d ago First seen · 52 lines · 40 tokens per session scan A 880c6e3b34a9
aws-kb is a command published in the GitHub repository odere-pro/claude-aws-architect (1 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 669 once invoked, about $0.0002 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
progress
View your CodeSensei learning dashboard — belt rank, XP, streaks, and skills.
recap
Get a summary of everything you learned this session — concepts, quizzes, and progress.
caiq-generate
Generate CAIQ (Consensus Assessments Initiative Questionnaire) responses.
map-framework
Map CSA CCM controls to other compliance frameworks.
cccs-guidance
CCCS assessment process and certified cloud provider guidance.
AWS Inspector Collect
Query AWS for compliance-relevant configuration across IAM, S3, CloudTrail, EBS, and emit findings conforming to the v1 contract.