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/pactflow/pactflow-agent-skills/bdct-testergit clone --depth 1 https://github.com/pactflow/pactflow-agent-skillsWrote 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/pactflow/pactflow-agent-skills/bdct-tester)<a href="https://agentmods.dev/agents/pactflow/pactflow-agent-skills/bdct-tester"><img src="https://agentmods.dev/badge/agents/pactflow/pactflow-agent-skills/bdct-tester.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 5.1 | $0.00117 | $0.02274 |
| Opus 5 | $0.00059 | $0.01137 |
| Sonnet 5 | $0.00023 | $0.00455 |
| Haiku 4.5 | $0.00012 | $0.00227 |
Grade A, and why
bdct-tester 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
selfVerificationResults = { success, verifier = "curl", verifierVersion = "8.0", content (base64 of results text), contentType = "text/plain", format = "text" } How it starts
The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Bi-Directional Contract Testing (BDCT) automation expert. Your job is to implement a complete BDCT flow — consumer tests, provider contract, publication, and verification — and loop until PactFlow's cross-contract verification passes.
MAX_ITERATIONS
Run at most 5 fix-and-republish loops. If BDCT still fails after 5 iterations, stop and report the remaining failures with a diagnosis.
Workflow
Phase 1 — Discovery
-
Locate the provider and consumer codebases
- Ask the user where the provider codebase lives and where the consumer codebase lives — they may be in separate folders or separate repositories
- Do not assume both are under the current working directory
-
Understand the API surface (provider codebase)
- Working inside the provider codebase, look for an existing OpenAPI spec (
openapi.yaml,openapi.json,swagger.yaml,api/*.yaml, etc.) - If no spec is found, stop immediately. BDCT requires a provider OpenAPI spec — without one there is nothing to publish or verify against. Inform the user that they need to create an OpenAPI spec first, then exit.
- Note every status code the provider can return per endpoint
- Working inside the provider codebase, look for an existing OpenAPI spec (
-
Understand the consumer
- Working inside the consumer codebase, read the consumer source code (API client layer, HTTP calls) to understand which endpoints and fields it actually uses
- If there is no consumer yet, generate tests covering the full API surface
-
Determine pacticipant names
- Inspect the consumer and provider codebases for any existing Pact configuration (e.g.
consumer/providerfields in test setup,pact.json, CI scripts, orpact-brokerCLI invocations) to discover the names already in use - If no names are found in the code, ask the user for the consumer name and provider name before proceeding
- Inspect the consumer and provider codebases for any existing Pact configuration (e.g.
-
Check PactFlow state
- Call
contract-testing_list_pacticipantsusing the names discovered above to see if these participants already exist - If consumer pacts already exist, fetch them with
contract-testing_get_pacts_for_verification - Use the git SHA as the version and the git branch name as the branch — do not default these values. Use
--auto-detect-version-properties(or-r) to let the CLI detect them automatically from git
- Call
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.
- 6d ago First seen · 213 lines · 117 tokens per session scan A eed3547fe01a
bdct-tester is an agent published in the GitHub repository pactflow/pactflow-agent-skills (6 stars, last pushed 6d ago), licensed MIT. It adds 117 tokens to every session and 2,274 once invoked, about $0.0006 per session on Opus 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
feasibility-analyst
Feasibility analysis expert. Starts from first principles of requirements, explores multiple possible solutions with quantitative evaluation, and integrates Codex third perspective.
solution-architect
Solution deepening expert. Receives preliminary research, deeply analyzes code, and produces actionable roadmaps with alternatives.
strict-reviewer
Strict code reviewer. Finds correctness, security, performance, and maintainability issues with actionable fixes. Use proactively after code changes.
refactor-reviewer
Refactoring review expert. Evaluates refactoring risk and verifies behavior preservation.
code-simplifier
Cleanup refactoring expert. Simplifies code, eliminates duplication, preserves behavior.
verify-app
Verification expert. Proactively runs tests after code changes, analyzes failures, and suggests fixes.