Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add odere-pro/claude-aws-architect/plugin install 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-spec)<a href="https://agentmods.dev/commands/odere-pro/claude-aws-architect/aws-spec"><img src="https://agentmods.dev/badge/commands/odere-pro/claude-aws-architect/aws-spec.svg" alt="Measured on agentmods" 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 | $0.00053 | $0.00967 |
| Opus 5 | $0.00026 | $0.00483 |
| Sonnet 5 | $0.00011 | $0.00193 |
| Haiku 4.5 | $0.00005 | $0.00097 |
Grade A, and why
aws-spec 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 7d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are running the claude-aws-architect spec validator against a per-feature spec folder.
Inputs
- Arguments:
$ARGUMENTS - Spec root:
.claude/specs/ - Plugin root:
${CLAUDE_PLUGIN_ROOT}(providestests/gates/run-all.shandtests/run-transcripts.sh).
Modes
The first argument is one of:
--list— list every feature folder under.claude/specs/with the status pulled from eachrequirements.mdfrontmatter.--show <feature>— print the artefact inventory for one feature: which ofrequirements.md,design.md,tasks.md,contracts/<slug>.md, anddiagrams.d2exist; the status of each spec doc; the citation count per artefact; the open-question count.--validate <feature>— run the deterministic and runtime gates that apply to the feature folder.
If the first argument is a feature slug with no flag, default to --show.
Validate mode — actions
When --validate is passed:
- Frontmatter and citation gates. For each of
requirements.md,design.md,tasks.mdunder.claude/specs/<feature>/, verify the spec-frontmatter rule: required keys (feature,created,updated,status,grounded-by),grounded-byminimum count (≥1 onrequirements.md), status values from the closed set (draft | review | accepted | implemented), and inline<server>:<short-key>citations resolving to entries in.grounding-ledger.json. - Component-contract gates. For every component named in
design.md, verify a matchingcontracts/<slug>.mdexists; the component-contract rule's required frontmatter (component,kind,version,status,talks-to,grounded-by) and seven canonical body sections (Purpose, Interface, Sequence, Component view, Acceptance criteria, Observability, Integration points) are present and in order; the observability triple records a concrete metric, log, and trace; integration links resolve to sibling slugs. - Diagram gates. Verify
diagrams.d2carries every required layer tag (c4-l1,c4-l2, onec4-l3-<container>per L2 container,seq-system,seq-component,seq-error). Verify no untagged top-level nodes; no orphan nodes. - Plugin gates. Run
${CLAUDE_PLUGIN_ROOT}/tests/gates/run-all.shand report PASS/WARN/FAIL per gate. - Transcript-replay schema gates. Run
${CLAUDE_PLUGIN_ROOT}/tests/run-transcripts.sh(validate-only) so the per-feature run does not regress the harness contract.
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.
- 7d ago First seen · 70 lines · 53 tokens per session scan A 62272818d801
aws-spec is a command published in the GitHub repository odere-pro/claude-aws-architect (1 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 967 once invoked, about $0.0003 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.
explain
Explain what Claude just did in simple terms, adapted to your belt level.
belt
View your current belt rank and progress toward the next one.
level
Set your preferred teaching level or tell CodeSensei about your background.
why
Understand why Claude made a specific decision or chose a particular approach.