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 agentmods add agents/akarazhev/bitcoin-risk-brief/openapigit clone --depth 1 https://github.com/akarazhev/bitcoin-risk-briefWrote 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/akarazhev/bitcoin-risk-brief/openapi)<a href="https://agentmods.dev/agents/akarazhev/bitcoin-risk-brief/openapi"><img src="https://agentmods.dev/badge/agents/akarazhev/bitcoin-risk-brief/openapi.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 | $0.00000 | $0.00319 |
| Opus 5 | $0.00000 | $0.00160 |
| Sonnet 5 | $0.00000 | $0.00064 |
| Haiku 4.5 | $0.00000 | $0.00032 |
Grade A, and why
openapi scanned grade A with 1 finding 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
This example downloads the live schema with `curl`, then generates a Python client with What it actually says
OpenAPI
The machine-readable OpenAPI schema is served at:
https://bitcoinriskbrief.minihub.app/api/openapi.json
It describes the seven public application endpoints: health, readiness, latest risk, risk history, risk levels, latest
brief, and waitlist submission, including route summaries, status codes, cache/no-store headers, and illustrative
response examples. Generated code does not enforce the product's interpretation rules: clients must still call
/api/readiness first and must not present any output as financial advice, investment advice, a price forecast, or a
trading recommendation.
Interactive documentation is deliberately absent. The strict Content-Security-Policy blocks the CDN-loaded assets used by the default Swagger UI, so the backend exposes the schema while leaving Swagger UI and ReDoc disabled. The CSP is not relaxed for documentation.
Generate a client
This example downloads the live schema with curl, then generates a Python client with
OpenAPI Generator:
curl --fail --silent --show-error \
https://bitcoinriskbrief.minihub.app/api/openapi.json \
--output bitcoin-risk-brief.openapi.json
openapi-generator-cli generate \
--input-spec bitcoin-risk-brief.openapi.json \
--generator-name python \
--output generated/bitcoin-risk-brief-python
Review generated method names and models before integrating them, and put the readiness-first gate in the calling workflow rather than assuming code generation adds 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.
- 4d ago First seen · 37 lines · 0 tokens per session scan A d1b089378c87
openapi is an agent published in the GitHub repository akarazhev/bitcoin-risk-brief (0 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 319 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
ladybug-architect
Deep work on the LadybugDB graph tier — the Graph API service, its client factory and routing middleware, the EC2/ASG fleet and its CloudFormation stacks, and the DynamoDB registries. Use for architecture review, query and memory performance tuning, ingestion and materialization issues, instance/volume…
growth-pulse-workflow
Agent "growth-pulse-workflow" from Treevu-ai/cli-market-world, covering por qué es distinto de price pulse, arquitectura, fuentes de datos (todas públicas, sin auth), cómo ejecutar and verificado (2026-07-12).
outbound-intelligence-agro
ICP: Export Managers, Revenue Strategists, and Innovation Directors in the Agro/Food sector. Goal: Sell CLI Market Intelligence Pilot ($300-$500/mo). Key Value: Eliminating commercial blindness in destination retail pricing using Golden Records.
report-sample-blueberries
Categoría: Arándanos / Blueberries Frecuencia: Cada 4 horas Golden Records Analizados: 12 SKUs normalizados Mercados: Perú (Origen/Local) vs. España (Destino/Referencia).
data-analytics-lead
CLI Market's internal Data & Analytics lead — owns catalog data quality, price/coverage metrics, moat health, and the search→cart→checkout funnel for both human and AI-agent consumers. Use PROACTIVELY when investigating qualityflagged spikes, coverage7dpct drops, stale collectors, cross-retailer dedup/normalization…
trellis-check
Code quality check expert. Reviews code changes against specs and self-fixes issues.