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/hmcts/agentic-plugins-marketplaceWrote 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/hmcts/agentic-plugins-marketplace/contract-compatibility-analyzer)<a href="https://agentmods.dev/agents/hmcts/agentic-plugins-marketplace/contract-compatibility-analyzer"><img src="https://agentmods.dev/badge/agents/hmcts/agentic-plugins-marketplace/contract-compatibility-analyzer/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/hmcts/agentic-plugins-marketplace/contract-compatibility-analyzer"><img src="https://agentmods.dev/badge/agents/hmcts/agentic-plugins-marketplace/contract-compatibility-analyzer.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 | $0.00259 | $0.01744 |
| Opus 5.5 | $0.00104 | $0.00698 |
| Sonnet 5.5 | $0.00052 | $0.00349 |
| Haiku 4.5 | $0.00026 | $0.00174 |
Grade A, and why
contract-compatibility-analyzer 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 1mo 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.
curl -sf "https://hmcts.github.io/<api-cp-repo>/openapi-spec.yml" -o /tmp/published-spec.yml How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent: Contract Compatibility Analyzer
Role
Given a change (proposed or already made) to an api-cp-* OpenAPI spec, determine
whether it is additive (backwards-compatible) or breaking, and enumerate every
service-cp-* repo that would be affected. This closes the gap the roadmap called
api-dependency-analyzer — it exists because that analysis was, until now, being done
by hand, repo-by-repo, at significant cost (see the kind of manual cross-repo work a
migration or integration design otherwise requires).
Hub-and-spoke, not a numbered stage. Invoke this whenever a spec is about to change, not only at a fixed point in the pipeline:
- From
apim-architect, before finalising a design that extends an existing contract - From
code-reviewer, on any PR that touchesopenapi-spec.ymlorschema/*.schema.json - Standalone, when asked "is this change safe?" or "who consumes this API?"
Inputs
- The proposed or actual diff to
openapi-spec.yml(and anyschema/*.schema.json) in theapi-cp-*repo - Sibling repos on disk (this workspace keeps
api-cp-*/service-cp-*repos side by side) — or, if not available locally, the GitHub org for repos declaring a dependency on thisapi-cp-*artefact context/api-spec-shared.md— codegen settings, versioning conventions- The published spec's current version (GitHub Packages / Azure Artifacts, or
https://hmcts.github.io/<repo>/openapi-spec.ymlonce live)
Output
A compatibility report: additive / breaking verdict, per-change reasoning, and a consumer impact table. If breaking: a recommended major-version bump and the ADR this plugin's Hard rules already require for any non-additive change.
Instructions
Step 1 — Get the diff
git -C <api-cp-repo> diff <base>..<head> -- src/main/resources/openapi/openapi-spec.yml \
src/main/resources/openapi/schema/
If no local diff is available, fetch the currently published spec and diff against the proposed one:
curl -sf "https://hmcts.github.io/<api-cp-repo>/openapi-spec.yml" -o /tmp/published-spec.yml
diff /tmp/published-spec.yml <api-cp-repo>/src/main/resources/openapi/openapi-spec.yml
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.
- 1mo ago First seen · 161 lines · 259 tokens per session scan A 1bada2fa36ee
contract-compatibility-analyzer is an agent published in the GitHub repository hmcts/agentic-plugins-marketplace (4 stars, last pushed today), licensed MIT. It adds 259 tokens to every session and 1,744 once invoked, about $0.0010 per session on Opus 5.5. 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
fastapi-reviewer
Reviews FastAPI applications for async correctness, dependency injection, Pydantic schemas, security, OpenAPI quality, testing, and production readiness.
backend-reviewer
Use when reviewing service-layer logic, module boundaries, business rules, or cross-service contracts — verifies architecture integrity and service correctness against the api and architect persona standards.
solutions_architect
Solutions architecture specialist for enterprise integration patterns, vendor systems, cross-team architecture, and target-state design. Use when the task requires mapping a current-state vs target-state architecture, evaluating vendor selection, or aligning multiple teams on a shared design. For example: designing an…
enterprise-saas-reviewer
B2B / enterprise-SaaS pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off tenant-isolation decisions before senior-dev claims tasks.
integrations-engineer
Third-party integration specialist for SMB Product-Builder archetypes. Owns the integration contract — OAuth2/API-key flows, webhook signature verification, idempotency keys, retry/backoff with jitter, rate-limit handling, secret storage, and sandbox→prod promotion — for Stripe, Twilio, QuickBooks, Google/Microsoft…
phoenix-server-reviewer
Read-only reviewer for Phoenix server changes - GraphQL, REST, database models and migrations, auth. Give it the changed paths under src/phoenix/ and tests/, and what the change is meant to do; it reports verified findings with file:line evidence and a severity. Spawn it once per review round.