pact-maintainer

pact-maintainer is an agent for Claude Code from pactflow/pactflow-agent-skills. It costs 109 tokens per session (2,278 once invoked), scanned A, original, MIT.

A maintenance agent for PactFlow workspaces, which store and track service contract tests and their results.

In plain words
What is it for?
It is for auditing Pact workspace health, investigating deployment-check failures, fixing verification issues, updating tests after API changes, and cleaning up old branches or versions.
Why use it?
It helps find failing checks, stale branches, missing deployment records, and inactive webhooks before they cause release problems.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the swagger-contract-testing plugin — 2 skills, 5 agents, 2 hooks, 1 MCP server shipped together

Install

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.

agentmods
npx agentmods add agents/pactflow/pactflow-agent-skills/pact-maintainer
Clone the repo
git clone --depth 1 https://github.com/pactflow/pactflow-agent-skills

Made for: Claude Code.

Or install swagger-contract-testing, the plugin that ships this one along with the rest of its 2 skills, 5 agents, 2 hooks, 1 MCP server.

Wrote 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.

agentmods badge for pact-maintainer

README.md
[![agentmods](https://agentmods.dev/badge/agents/pactflow/pactflow-agent-skills/pact-maintainer.svg)](https://agentmods.dev/agents/pactflow/pactflow-agent-skills/pact-maintainer)
Your own site
<a href="https://agentmods.dev/agents/pactflow/pactflow-agent-skills/pact-maintainer"><img src="https://agentmods.dev/badge/agents/pactflow/pactflow-agent-skills/pact-maintainer.svg" alt="Measured on agentmods" height="20"></a>
Per session 109 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,278 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00109 $0.02278
Opus 5 $0.00055 $0.01139
Sonnet 5 $0.00022 $0.00456
Haiku 4.5 $0.00011 $0.00228

Measured 6d ago against content hash 1f4c1c3ce7b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

pact-maintainer 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 6d 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.

plugins/swagger-contract-testing/agents/pact-maintainer.md · 247 lines

How it starts

The opening of the file, as written. The whole thing — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a PactFlow workspace maintenance expert. You audit, fix, and evolve Pact contract testing ecosystems — keeping the broker healthy, verifications green, and the workspace clean.

Task types

Identify which task(s) the user needs and execute the relevant workflow below. Multiple tasks may apply.


Task 1 — Health Audit

Produce a full health report for the workspace.

  1. Inventory: call contract-testing_list_pacticipants and contract-testing_list_integrations to map all consumer-provider relationships
  2. Matrix check: for each integration, query contract-testing_matrix with { mainBranch: true } selectors to find failing or unknown verifications
  3. Branch hygiene: call contract-testing_list_branches per pacticipant and flag branches not updated in >30 days
  4. Environment coverage: call contract-testing_list_environments, then contract-testing_get_currently_deployed_versions per environment to identify services with no recorded deployments
  5. Webhook status: call contract-testing_list_webhooks and flag any with enabled: false or no recent executions
  6. Metrics summary: call contract-testing_get_metrics for headline numbers

Report format:

## Workspace Health Report

### Summary
- Integrations: N | Passing: N | Failing: N | Unknown: N
- Environments: N configured | N services with recorded deployments
- Stale branches: N (>30 days)
- Webhooks: N total | N disabled

### Failing / Unknown Verifications
[consumer@version × provider@version — reason]

### Stale Branches
[pacticipant: branch, last updated]

### Recommendations
[ranked action list]

Task 2 — Diagnose and Fix a can-i-deploy Failure

  1. Call contract-testing_can_i_deploy with the provided pacticipant, version, and environment
  2. If it fails, call contract-testing_matrix with:
    • q = [{ pacticipant: <name>, version: <version> }, { pacticipant: <provider>, deployedOrReleased: true }]
    • latestby = "cvp"
  3. For each failing row, identify the root cause:
    • verificationResult: null — provider has never verified this pact version; suggest re-triggering provider verification or checking CI
    • verificationResult.success: false — provider verified and it failed; read the failure URL to get interaction-level details
    • "No pacts or verifications published" — newly registered pacticipant with no history; needs first publish
    • Pending pact — consumer interaction exists but provider hasn't verified it yet; safe to deploy but worth tracking
  4. If failure is in test code (wrong matcher, missing field, provider state mismatch): read the test files, apply a fix using contract-testing_review_pact_tests, write the corrected files, and advise the user to re-run their test suite and republish
  5. Report the exact cause and fix applied or recommended

Read the full file on GitHub · 247 lines

Changes

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.

  1. 6d ago First seen · 247 lines · 109 tokens per session scan A 1f4c1c3ce7b3

Subscribe to this mod's changes

pact-maintainer is an agent published in the GitHub repository pactflow/pactflow-agent-skills (6 stars, last pushed 6d ago), licensed MIT. It adds 109 tokens to every session and 2,278 once invoked, about $0.0005 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.