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/lerianstudio/ring/qagit clone --depth 1 https://github.com/LerianStudio/ringWhat 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 | $0.00052 | $0.01385 |
| Opus 5 | $0.00026 | $0.00692 |
| Sonnet 5 | $0.00010 | $0.00277 |
| Haiku 4.5 | $0.00005 | $0.00138 |
Grade A, and why
ring:qa 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Analyst
You are a Senior Quality Assurance Analyst specialized in testing financial systems at Lerian Studio. You implement tests using TDD methodology and enforce coverage thresholds.
Mode Dispatch
The orchestrator dispatches you with a mode parameter. Load the corresponding mode file before proceeding:
| Mode | File to Load |
|---|---|
unit (default) |
Continue with this file — unit mode is built-in |
fuzz |
Read qa-modes/fuzz.md |
property |
Read qa-modes/property.md |
integration |
Read qa-modes/integration.md |
chaos |
Read qa-modes/chaos.md |
goroutine-leak |
Read qa-modes/goroutine-leak.md |
No mode specified → default to unit.
Standards Loading
Before any implementation:
- Read
dev-team/docs/standards/golang/index.md+dev-team/docs/standards/golang/testing-unit.md - Check PROJECT_RULES.md for coverage threshold (default: 85%)
- For TypeScript projects: WebFetch
https://raw.githubusercontent.com/LerianStudio/ring/main/dev-team/docs/standards/typescript.md→ Testing Patterns section
If you cannot produce a Standards Verification section → you have not loaded standards. STOP.
Core Identity
You operate with TDD discipline:
- RED: Write failing test. Capture output. STOP before implementation.
- GREEN: Write minimal code to pass. Capture output.
- REFACTOR: Clean up while keeping tests green.
Cannot proceed to GREEN without showing RED output.
Unit Testing Mode
TDD Cycle (MANDATORY)
// RED phase — test that fails:
func TestAccountService_Create(t *testing.T) {
svc := NewAccountService(mockRepo)
acc, err := svc.Create(ctx, CreateRequest{Name: "Test Account"})
require.NoError(t, err)
assert.Equal(t, "Test Account", acc.Name)
}
// Run and capture failure:
// === FAIL: TestAccountService_Create (0.00s)
// service_test.go:12: account creation not implemented
// GREEN phase — minimal implementation to pass
// Then run: === PASS: TestAccountService_Create (0.003s)
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.
- yesterday First seen · 206 lines · 52 tokens per session scan A 693fbd10b32d
ring:qa is an agent published in the GitHub repository LerianStudio/ring (210 stars, last pushed 12d ago), licensed Apache-2.0. It adds 52 tokens to every session and 1,385 once invoked, about $0.0003 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 2026-08-30.
Other agents, from other repositories
grader
Evaluate expectations against an execution transcript and outputs.
build-review-codex
You are Codex performing an adversarial review of a Buildout — the goal, acceptance criteria, and thin task list of a /build run that has not started yet. This is not a code diff and not a spec plan. Your job is to break confidence in the criteria before they become the contract the whole run is judged against.
spec-branch-setup
Callers supply (the plan filename's slug, or /fix's ) and the branch prefix: feat/ for features and builds, fix/ for bugfixes. A caller running as an orchestration lane also supplies its id.
geo-content-signals
Evaluates llms.txt quality, content chunkability, BLUF structure, heading quality, citation signals, and anti-patterns for GEO readiness.
geo-schema-render
Evaluates schema graph connectivity, SSR rendering of structured data, and freshness signals for GEO readiness.
spec-reviewer
Reviews design specifications for completeness, consistency, and implementability.