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 skills add odere-pro/claude-aws-architect --skill aws-grounding-cachegit 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/skills/odere-pro/claude-aws-architect/aws-grounding-cache)<a href="https://agentmods.dev/skills/odere-pro/claude-aws-architect/aws-grounding-cache"><img src="https://agentmods.dev/badge/skills/odere-pro/claude-aws-architect/aws-grounding-cache/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/skills/odere-pro/claude-aws-architect/aws-grounding-cache"><img src="https://agentmods.dev/badge/skills/odere-pro/claude-aws-architect/aws-grounding-cache.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 | $0.00061 | $0.01303 |
| Opus 5 | $0.00030 | $0.00651 |
| Sonnet 5 | $0.00012 | $0.00261 |
| Haiku 4.5 | $0.00006 | $0.00130 |
Grade A, and why
aws-grounding-cache 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.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to Use
Apply this skill any time an agent has just made a successful MCP call and needs to record the citation, or any time an agent needs to look up an existing citation before deciding whether to re-fetch. The discovery agent owns the write-side; every reader (orchestrator, solution-architect, implementation, security, cost) consults it before issuing a new MCP call.
Trigger conditions:
- An MCP call returned successfully and the result must be cached.
- An agent is about to issue an MCP call and wants to check whether a fresh citation already exists in the ledger.
- A short-key needs to be derived for a new query.
- A short-key collision was detected at write-time.
- An entry's TTL has elapsed and the agent is deciding whether to re-fetch or surface a stale-data marker.
- The orchestrator is flushing a
conflict_resolutionentry produced by the merge contract (the orchestrator is the writer; this skill provides the schema and the write path).
Procedure
- Locate the ledger file. It lives at
.claude/specs/<feature>/.grounding-ledger.json, git-ignored. If the file does not exist for the current feature, create it fromassets/grounding-ledger.json.tmpl. - Derive the short-key. Canonicalise the query (lowercase, collapse whitespace, sort URL parameters), take SHA-1, and use the first 8 hex chars. Full algorithm and collision behaviour in
references/collision-policy.md. - Check for an existing entry. If a short-key matches and the entry is within its TTL (per
references/ttl-policy.md), return it; do not issue a new MCP call. - Redact before writing. Run the result through the redaction patterns before persistence: AWS access keys, secret keys, session tokens, account IDs in IAM/STS/S3 context, ARNs with embedded sessions, pre-signed URL signatures, and the
aws_*_keyregex family. Full pattern catalogue, application order, and failure handling inreferences/redaction-policy.md. The unredacted result must never reach disk; redaction failure aborts the write. - Insert with the canonical schema. Each entry carries
server,tool,query,retrieved(ISO-8601 UTC),result_summary, andttl-class. Schema rules inreferences/ledger-schema.md. - Dedupe. If a write would produce a duplicate
(server, short-key)pair, the new entry replaces the old one andretrievedis updated. Do not append silently — duplicates are an error in the calling agent. - Expire on read. When a reader looks up an entry, compare
retrievedto the TTL window for the entry'sttl-class. If expired, surface the stale-data flag to the caller; do not return the value as if it were fresh.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 62 lines · 61 tokens per session scan A 8a882e8da02d
aws-grounding-cache is a skill published in the GitHub repository odere-pro/claude-aws-architect (1 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 1,303 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 skills, from other repositories
deployment
Hosting, deployment, CI/CD, and going live. Activated when Claude works with deployment configs, Dockerfiles, Vercel/Netlify configs, or deployment-related commands.
ec2
AWS EC2 virtual machine management — instances, security groups, key pairs, AMIs, EBS volumes, Auto Scaling Groups, Spot Instances, Session Manager, placement groups, and instance lifecycle automation. Trigger on ANY of these, even when EC2 isn't named explicitly: - Launching or provisioning: "spin up a server"…
cloudwatch
AWS CloudWatch monitoring for logs, metrics, alarms, and dashboards. Use when setting up monitoring, creating alarms, querying logs with Insights, configuring metric filters, building dashboards, or troubleshooting application issues.
ecs
AWS ECS container orchestration for running Docker containers. Use when deploying containerized applications, configuring task definitions, setting up services, managing clusters, or troubleshooting container issues.
cloudformation
AWS CloudFormation infrastructure as code for stack management. Use when writing templates, deploying stacks, managing drift, troubleshooting deployments, or organizing infrastructure with nested stacks.
eks
AWS EKS Kubernetes management for clusters, node groups, and workloads. Use when creating clusters, configuring IRSA, managing node groups, deploying applications, or integrating with AWS services.