Borrowing it
Nothing to install: this file belongs to asbrodova/aura-tracker-gcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/asbrodova/aura-tracker-gcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/asbrodova/aura-tracker-gcpWrote 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/instructions/asbrodova/aura-tracker-gcp/claude-md)<a href="https://agentmods.dev/instructions/asbrodova/aura-tracker-gcp/claude-md"><img src="https://agentmods.dev/badge/instructions/asbrodova/aura-tracker-gcp/claude-md/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/instructions/asbrodova/aura-tracker-gcp/claude-md"><img src="https://agentmods.dev/badge/instructions/asbrodova/aura-tracker-gcp/claude-md.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 | $0.02798 | $0.02798 |
| Opus 5 | $0.01399 | $0.01399 |
| Sonnet 5 | $0.00560 | $0.00560 |
| Haiku 4.5 | $0.00280 | $0.00280 |
Grade A, and why
aura-tracker-gcp CLAUDE.md 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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Commands
# Build
go build ./...
# Test (always use -race)
go test -race ./...
# Single package
go test -race ./internal/gcp/... -run TestAggregateBottlenecks
# Vet
go vet ./...
# Run server
GCP_PROJECT_ID=my-project go run ./cmd/aura-tracker-gcp
# Smoke-test tools/list
echo '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}' \
| GCP_PROJECT_ID=my-project go run ./cmd/aura-tracker-gcp
Architecture
Hexagonal Architecture. The hexagon boundary is ports/gcp_service.go.
cmd/ ──► internal/mcp/ ──► ports/GCPService
cmd/ ──► internal/gcp/ ──► ports/GCPService
internal/gcp/ ──► GCP SDK
internal/mcp/ NEVER imports internal/gcp/
go build ./internal/mcp/... compiles zero GCP SDK code.
Application-layer engines live between MCP and the port: internal/diagnostics for incidents, internal/costreasoning for cost explanations, internal/securityaudit for deterministic security posture findings and scoring, internal/diagram for architecture scoping and deterministic rendering, and internal/drift for symmetric cross-environment configuration comparison. They depend on narrow interfaces satisfied by ports.GCPService and never import GCP SDK packages.
Environment Variables
| Variable | Required | Description |
|---|---|---|
GCP_PROJECT_ID |
Yes* | Legacy single-project setting. Omit when using YAML environments or GCP_ENVIRONMENTS_JSON. |
GCP_ENVIRONMENTS_JSON |
No | JSON array of {project_id, alias, default} entries. Multiple entries require aliases and exactly one default. |
GOOGLE_APPLICATION_CREDENTIALS |
No | Service account key path (optional with ADC) |
ANONYMIZE_ENABLED |
No | Set true to enable PII scrubbing on all tool outputs (overrides YAML enabled) |
ANONYMIZE_CONFIG_PATH |
No | Path to YAML config file for the anonymization engine |
ANONYMIZE_PROJECT_ID |
No | Masks an unaliased project as [GCP_PROJECT_ID]. Configured aliases are always enforced on MCP output. |
RECOMMENDER_ENABLED |
No | Set false to disable Cloud Recommender API integration. On by default. Enriches Aura Scores with idle/overprovisioned signals; 12h cache prevents quota exhaustion. |
RECOMMENDER_BQ_EXPORT_ENABLED |
No | Set true to enable the gcp_export_recommendations_to_bq MCP tool. Off by default. |
RECOMMENDER_BQ_EXPORT_DATASET |
No | BigQuery dataset name for the recommendations export (overrides recommender_export.dataset in YAML). |
COST_REASONING_ENABLED |
No | Set true to register the read-only gcp_cost_explain tool. Off by default. |
COST_REASONING_SOURCES_JSON |
No | Strict JSON array mapping configured environments to query/export projects and billing datasets. Mutually exclusive with YAML sources and legacy source settings. |
COST_QUERY_PROJECT_ID |
No | Project that owns BigQuery query jobs. Defaults to GCP_PROJECT_ID. |
BILLING_EXPORT_PROJECT_ID |
No | Project containing the detailed billing export. Defaults to the query project. |
BILLING_EXPORT_DATASET |
Cost only | Required dataset containing gcp_billing_export_resource_v1_*. |
BILLING_EXPORT_TABLE |
No | Optional exact detailed billing table; otherwise the sole matching table is discovered. |
COST_REASONING_TIMEZONE |
No | IANA timezone for complete-day comparisons. Default UTC. |
COST_REASONING_HISTORY_DAYS |
No | Billing history window, 14–366 days. Default 90. |
COST_QUERY_MAX_BYTES |
No | Per-statement BigQuery bytes-billed ceiling. Default 5 GiB. |
GRAPHVIZ_DOT_PATH |
No | Path to Graphviz dot for SVG architecture diagrams. Mermaid and Graphviz DOT source do not require it. |
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 · 211 lines · 2,798 tokens per session scan A cf23de2daf72
aura-tracker-gcp CLAUDE.md is an instructions file published in the GitHub repository asbrodova/aura-tracker-gcp (5 stars, last pushed today), licensed Apache-2.0. It adds 2,798 tokens to every session, about $0.0140 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.