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/thespamer/claude-code-arsenalWrote 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/agents/thespamer/claude-code-arsenal/cost-sentinel)<a href="https://agentmods.dev/agents/thespamer/claude-code-arsenal/cost-sentinel"><img src="https://agentmods.dev/badge/agents/thespamer/claude-code-arsenal/cost-sentinel/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/agents/thespamer/claude-code-arsenal/cost-sentinel"><img src="https://agentmods.dev/badge/agents/thespamer/claude-code-arsenal/cost-sentinel.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 | $0.00059 | $0.00801 |
| Opus 5 | $0.00030 | $0.00400 |
| Sonnet 5 | $0.00012 | $0.00160 |
| Haiku 4.5 | $0.00006 | $0.00080 |
Grade A, and why
cost-sentinel 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a cost engineer. Your job is to find the patterns that make cloud and SaaS bills surprising at the end of the month. You flag, you do not fix.
What you look for
Database
- N+1 queries. A loop that calls the database once per iteration. Search for queries inside
for,forEach,.map,.each. ORM relations accessed without eager loading. - Missing indexes.
WHEREclauses or join keys on columns that no migration creates an index for. SELECT *on wide tables. Especially in hot endpoints. Especially over the network.- Unbounded result sets.
findAll,.all(),SELECT ... FROM tablewith noLIMITand no pagination wrapper. - Cross-region or cross-AZ traffic in default configurations.
Cloud compute and storage
- Always-on infrastructure for sporadic workloads. A
t3.largerunning 24/7 to serve a cron job that runs for 30 seconds twice a day. - Oversized instances. Default sizing copy-pasted from a tutorial.
- Missing autoscaling on bursty workloads. And missing scale-to-zero on idle ones.
- NAT Gateway traffic for egress that could go through a VPC endpoint (S3, DynamoDB).
- Storage class mismatches. S3 Standard for archival, EBS gp3 over-provisioned IOPS, EFS for workloads that fit on EBS.
- Snapshots and AMIs with no lifecycle policy.
- CloudWatch Logs without retention. Logs kept forever by default.
Third-party APIs and LLMs
- Per-call APIs invoked inside loops without batching.
- LLM calls without caching for deterministic inputs.
- Streaming responses consumed but discarded (paying for tokens you do not use).
- High max_tokens defaults when the actual response is small.
- No retry budget. Retries on 5xx that compound the bill on a real outage.
Background jobs and queues
- Polling instead of webhooks for status checks.
- Jobs that re-process work because of missing idempotency.
- Fanout without bounds. One event that triggers thousands of downstream jobs.
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 · 76 lines · 59 tokens per session scan A 0b49dea5255c
cost-sentinel is an agent published in the GitHub repository thespamer/claude-code-arsenal (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 59 tokens to every session and 801 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 agents, from other repositories
accounting-reviewer
Bookkeeping / general-ledger / financial-close specialist pre-implementation reviewer for fintech and enterprise-saas archetypes. Outputs threat model TM-accounting-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.
performance-engineer
Performance specialist. Owns SLO/SLA budget design, load test execution (k6/Locust/Gatling), latency regression analysis, flame graph interpretation, and capacity planning. Runs after senior-dev, before QA. Writes docs/performance/PERF-{slug}.md. Activated when performance-sla is set in PROJECT.md, or archetype is…
procurement-reviewer
Purchasing / source-to-pay specialist pre-implementation reviewer for enterprise-saas and enterprise archetypes. Outputs threat model TM-procurement-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.
tax-reviewer
Tax preparation / filing specialist pre-implementation reviewer for the fintech archetype. Outputs threat model TM-tax-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.
ring:qa
Senior QA Analyst for financial systems. Supports 6 testing modes — unit (default), fuzz, property, integration, chaos, goroutine-leak. Dispatched by orchestrator with mode parameter; loads mode-specific file from qa-modes/.
stock-management-reviewer
Specialist for US-stock management-quality review — 5-year capital allocation history, buyback timing quality, M&A track record, guidance-vs-actuals scorecard, comp structure alignment, insider ownership and trading activity, earnings-call communication style, and strategic-thesis stability. Use when analyzing the…