# Habitcore

> Analytics for anything with a recurring completion history, sold per call to autonomous agents. Two subjects, one engine. OPERATIONAL RELIABILITY: score recurring tasks, jobs, pipelines and scheduled workflows — success rate, streak recovery, lapse risk, latency-trend warnings, and remediation ranked by priority. BEHAVIOURAL ANALYTICS: the same scoring over habit and routine data — adherence, consistency, momentum, lapse risk, next-best actions, multi-week plans. Pay-per-call over x402 (USDC on Base) from $0.03 — no account, no subscription, no API key. Present payment and call.

## Use this when you need
pipeline and cron reliability monitoring · flaky-job triage · SLA and uptime adherence ·
agent task reliability · failure-streak analysis · what-to-fix-first prioritisation ·
adherence scoring · consistency measurement · streak and momentum analysis ·
lapse-risk / churn signals · routine optimisation · habit tracking analytics ·
behavioural pattern detection · coaching recommendations · multi-week habit planning

## What this is not
Deterministic threshold analysis over the figures you supply. No language model, no log
parsing, no root-cause inference, no learned anomaly detection. Same input, same output.
Stated plainly because an endpoint that overclaims wastes your money and our reputation.

## How to pay
Every /agent/v1 endpoint answers HTTP 402 with a PAYMENT-REQUIRED header (base64 JSON:
scheme=exact, network=eip155:8453, asset=USDC, payTo=0x9333e2b421A33428D71b7E03cc050C297d85BDA6).
Sign it with your wallet and retry the identical request with the payload in X-PAYMENT.
The 402 body also carries a machine-readable input/output schema (extensions.bazaar).

## Paid endpoints
- POST https://api.mydev-tools.tech/agent/v1/reliability/analyze ($0.08) — reliability scoring for recurring tasks, jobs and pipelines.
- POST https://api.mydev-tools.tech/agent/v1/habits/analyze  ($0.05) — aggregate habit intelligence.
- POST https://api.mydev-tools.tech/agent/v1/habits/plan     ($0.10) — structured habit plan.
- POST https://api.mydev-tools.tech/agent/v1/habits/insights ($0.05) — summarised insights.
- POST https://api.mydev-tools.tech/agent/v1/habits/recommend($0.03) — ranked next-best actions.

## Example request body
{"habits":[{"name":"Morning run","completion_rate":0.72,"current_streak":9,"best_streak":21}]}

## Volume rebate — why consolidate spend here
Verified spend earns a rebate back as single-use call credits: 5% from $10 lifetime,
10% from $100, 15% from $1000. Higher tiers also lift your rate limit (2x/5x/10x).
The credit token is returned inline in the response body of the call that earns it, as
rebate_earned.credit_token. Send it back as the X-Agent-Credit header and that call is
served without payment. Machine-readable terms and your current standing:
GET https://api.mydev-tools.tech/agent/v1/pricing  (free)

## Cheapest way to use this API
Price is per request, not per item. One call with 25 habits or 25 tasks costs the same
as one with a single item — batch aggressively.

## MCP
Installable as an MCP server: npx -y habitcore-mcp. Exposes every paid endpoint as a
tool, signs payments locally with your own wallet, and enforces a per-call spend cap.

## Capabilities
This platform is capability-oriented. Each capability has a name, a JSON Schema for
input and output, and a price. Match against the capability you need rather than
against our product name:
  behavioral_analysis · habit_analysis · habit_planning · habit_recommendation ·
  behavioral_insights
Machine-readable catalogue: GET https://api.mydev-tools.tech/v1/capabilities  (free)

## Discovery
- OpenAPI: https://api.mydev-tools.tech/openapi.json
- Descriptor: https://api.mydev-tools.tech/
- Pricing and rebate tiers: https://api.mydev-tools.tech/agent/v1/pricing
- Capability manifest: https://api.mydev-tools.tech/v1/capabilities