memory-service: Skill for Claude Code

.skills/go-bdd/SKILL.md

go-bdd is a skill for Claude Code, Codex from chirino/memory-service. It costs 67 tokens per session (833 once invoked), scanned A, original, Apache-2.0.

A skill for testing REST and gRPC APIs with a Go behavior-driven development (BDD) suite. BDD describes expected behavior as readable scenarios, often in feature files, rather than testing only individual functions.

In plain words
What is it for?
Writing, editing, or debugging Go feature files, step definitions, test runners, and the test harness for REST and gRPC services.
Why use it?
It provides a consistent way to check API behavior across databases and configurations and to understand failures.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is chirino/memory-service's own configuration. It tells Claude Code and Codex how to work on memory-service itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything memory-service configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is CGO_ENABLED=1 go test -race -tags='sqlite_fts5 auth_testfixtures' ./internal/bdd -run '^TestFeaturesSQLite$' -count=1 > test.log 2>&1.

Reuse

Borrowing it

Nothing to install: this file belongs to chirino/memory-service. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/chirino/memory-service/main/.skills/go-bdd/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/chirino/memory-service

Made for: Claude Code, Codex.

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 go-bdd

README.md
[![agentmods](https://agentmods.dev/badge/skills/chirino/memory-service/go-bdd/github.svg)](https://agentmods.dev/skills/chirino/memory-service/go-bdd)
Your own site
<a href="https://agentmods.dev/skills/chirino/memory-service/go-bdd"><img src="https://agentmods.dev/badge/skills/chirino/memory-service/go-bdd/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.

agentmods 80×15 button for go-bdd

Your own site · 80×15
<a href="https://agentmods.dev/skills/chirino/memory-service/go-bdd"><img src="https://agentmods.dev/badge/skills/chirino/memory-service/go-bdd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 833 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00067 $0.00833
Opus 5.5 $0.00027 $0.00333
Sonnet 5.5 $0.00013 $0.00167
Haiku 4.5 $0.00007 $0.00083

Measured 1mo ago against content hash 328df99b6b39, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

go-bdd 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 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.

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.

.skills/go-bdd/SKILL.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Go BDD Suite

Test REST and gRPC behavior with the Go BDD suite (internal/bdd) rather than unit tests with mocks. Keep unit tests for internal helpers and infrastructure.

For the commands, build tags, and which runners need auth_testfixtures, use the build-test skill.

Layout

  • Shared features live in internal/bdd/testdata/features/ (REST) and features-grpc/. Backend-specific features go in sibling features-<backend>/ directories instead of copying the shared suite.
  • Each datastore or config has its own runner, internal/bdd/cucumber_<backend>*_test.go, with a matching TestDB implementation (testdb_<backend>.go).
  • Outbox behavior has dedicated runners (TestFeaturesPgOutbox, TestFeaturesSQLiteOutbox, TestFeaturesMongoOutbox). The broad suites keep the default config.

Feature files are API documentation

A reader should understand the API from the feature file without reading step code.

The first time a scenario uses an API, spell out the raw HTTP call and the JSON:

When I call POST "/v1/conversations/${conversationId}/entries" with body:
"""
{
  "channel": "HISTORY",
  "contentType": "history",
  "content": [{"text": "Hello", "role": "USER"}]
}
"""
Then the response status should be 201
And the response body should be json:
"""
{
  "id": "${response.body.id}",
  "conversationId": "${conversationId}",
  "channel": "history",
  "contentType": "history",
  "content": [{"text": "Hello", "role": "USER"}],
  "createdAt": "${response.body.createdAt}"
}
"""

After that, shorthand steps are fine:

Given the conversation has an entry "Hello"
When I list entries for the conversation
Then the response should contain 1 entry

Capture values for later steps with And set "myVar" to the json response field "id" and use them as ${myVar}.

Scenario isolation

Scenarios run concurrently, so each one gets a short suffix (internal/testutil/cucumber).

  • Canonical users (alice, bob, ...) and agent client IDs are rewritten to isolated values in request paths, bodies, gRPC prototext, and the X-Client-ID header. Responses are rewritten back before assertions.
  • When production auth metadata must match a user ID embedded in a request body (for example a user/<id> memory namespace), build it from TestScenario.IsolatedUser (or IsolatedClientID), not a literal name.
  • Roles: see internal/bdd/role_users_test.go. Use bob or erin when a scenario must prove isolation between ordinary users.
  • SQLite runners start a server and database file per scenario. The serial PostgreSQL and MongoDB runners share one server and run with concurrency 1.
  • On MongoDB runs, SQL verification steps are skipped (MongoTestDB.ExecSQL returns no rows). Add Mongo-specific assertions when datastore state matters.
  • godog.Table.Rows includes the header row; skip it in table-driven steps.

Read the full file on GitHub · 76 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. 1mo ago First seen · 76 lines · 67 tokens per session scan A 328df99b6b39

Subscribe to this mod's changes

go-bdd is a skill published in the GitHub repository chirino/memory-service (12 stars, last pushed yesterday), licensed Apache-2.0. It adds 67 tokens to every session and 833 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-26.

Related

Other skills, from other repositories

server-side-calls

Call tRPC procedures directly from server code using t.createCallerFactory() and router.createCaller(context) for integration testing, internal server logic, and custom API endpoints. Catch TRPCError and extract HTTP status with getHTTPStatusCodeFromError(). Error handling via onError option.

trpc/trpc · 61 tokens

mem0-test-integration

Verify a Mem0 integration produced by /mem0-integrate. Runs in the same workspace on the same branch (loose coupling) — installs dependencies, runs the repo's native test suite, then exercises a real end-to-end smoke flow against the user's API key. Produces a scorecard. TRIGGER when: user has just run /mem0-integrate…

mem0ai/mem0 · 207 tokens

prowler-test-api

Testing patterns for Prowler API: JSON:API, Celery tasks, RLS isolation, RBAC. Trigger: When writing tests for api/ (JSON:API requests/assertions, cross-tenant isolation, RBAC, Celery tasks, viewsets/serializers).

prowler-cloud/prowler · 62 tokens

python-sdk

Implement or modify Python SDK behavior under python/composio, including tools, toolkits, sessions, auth configs, connected accounts, client integration, and shared Python models. Use for Python core runtime/API work; pair with python-testing and cross-sdk-parity when TypeScript must match.

ComposioHQ/composio · 60 tokens

voiden

Create and edit Voiden .void files for API testing. Covers the .void file format and all enabled extension block types.

VoidenHQ/voiden · 28 tokens

convex-test

Generate convex-test tests for the app's Convex functions.

openclaw/clawhub · 16 tokens