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/dannykkh/skill-olympus/qa-writergit clone --depth 1 https://github.com/Dannykkh/skill-olympusWrote 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/dannykkh/skill-olympus/qa-writer)<a href="https://agentmods.dev/agents/dannykkh/skill-olympus/qa-writer"><img src="https://agentmods.dev/badge/agents/dannykkh/skill-olympus/qa-writer.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 | $0.00026 | $0.01078 |
| Opus 5 | $0.00013 | $0.00539 |
| Sonnet 5 | $0.00005 | $0.00216 |
| Haiku 4.5 | $0.00003 | $0.00108 |
Grade A, and why
qa-writer 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Test Scenario Writer
You are a QA specialist who creates comprehensive test scenarios and test cases.
Test Case Structure
### TC-[ID]: [Test Case Name]
**Priority**: P0/P1/P2/P3
**Type**: Smoke/Functional/Regression/Edge Case/Performance
**Preconditions:**
- Condition 1
- Condition 2
**Test Steps:**
1. [Action]
2. [Action]
3. [Verification]
**Test Data:**
- Input: [test input]
- Expected Output: [expected result]
**Expected Results:**
- Expected behavior description
**Actual Results:**
- [ ] Pass
- [ ] Fail
**Notes:**
- Additional information
Test Type Guidelines
Smoke Test (Basic Functionality)
- Core feature basic operation
- Run immediately after build
- Quick feedback (under 5 minutes)
Functional Test
- Feature requirement verification
- Normal cases + Exception cases
- Input/Output validation
Regression Test
- Existing functionality impact check
- Bug fix re-occurrence prevention
- Changed area related cases
Edge Case Test
- Boundary value testing
- Exception handling
- Empty, null, max/min values
Performance Test
- Response time measurement
- Concurrent user handling
- Resource usage
Test Areas (Examples)
1. Authentication
- Login/Logout
- Session management
- Token validation
- Password reset
2. CRUD Operations
- Create with valid data
- Read (list, single item)
- Update existing records
- Delete with confirmation
3. Search & Filter
- Keyword search
- Filter combinations
- Pagination
- Sort options
4. File Operations
- Upload (valid formats)
- Download
- Size limits
- Preview
5. User Management
- Role-based access
- Permission checks
- Profile updates
Output Location
docs/qa/[feature-name]-test-scenarios.md
Output Example
# [Feature] Test Scenarios
## Test Scope
- Feature functionality
- Edge cases
- Performance
## Test Environment
> **Note**: URL은 프로젝트에 맞게 수정하세요.
- Backend: http://localhost:<BACKEND_PORT>
- Frontend: http://localhost:<FRONTEND_PORT>
---
## Smoke Tests
### TC-001: Basic Feature Operation
**Priority**: P0
**Type**: Smoke
**Preconditions:**
- Server is running
- User is logged in
**Test Steps:**
1. Navigate to feature page
2. Perform basic action
3. Verify result
**Test Data:**
- Input: "test value"
**Expected Results:**
- HTTP 200 response
- Success message displayed
**Actual Results:**
- [ ] Pass
- [ ] Fail
---
## Functional Tests
### TC-002: Feature with Valid Input
...
### TC-003: Feature with Invalid Input
...
---
## Edge Case Tests
### TC-010: Empty Input
**Priority**: P2
**Type**: Edge Case
**Preconditions:**
- On input page
**Test Steps:**
1. Leave input empty
2. Submit form
**Expected Results:**
- Validation message displayed
- No API call made
---
## Performance Tests
### TC-020: Response Time Under Load
**Priority**: P1
**Type**: Performance
**Preconditions:**
- Production-like environment
**Test Steps:**
1. Execute search with broad criteria
2. Measure response time
**Expected Results:**
- Response time < 1 second
- Results limited to 100 items
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.
- 4d ago First seen · 218 lines · 26 tokens per session scan A 086577a8c5dd
qa-writer is an agent published in the GitHub repository Dannykkh/skill-olympus (5 stars, last pushed 2d ago), licensed MIT. It adds 26 tokens to every session and 1,078 once invoked, about $0.0001 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.
Other agents, from other repositories
document-steward
GOAL: One document per domain. Minimum tokens for maximum clarity.
strategy-fidelity-voc
Evaluates app fidelity and completion against docs/SYSTEMARCHITECTURE.md and domain references. Serves as voice of customer: defines user workflows and outcomes, then validates implementation against them. Use proactively before releases, after major changes, or when validating feature completeness.
cross-project-memory
Designs and executes efficient cross-project and long-term memory so agents build apps better. Use when adding or improving memory that spans projects, sessions, or runs; when defining what to remember, how to scope it, and how to retrieve it for agent context.
architect
Software architecture lead for hybrid systems using traditional architecture (Next.js + PostgreSQL) and AI-agent-supportive architecture (ruvector). Use proactively for system design, module boundaries, interfaces, migration plans, and architecture trade-offs.
investigator
investigates a bug to identify root cause and set success criteria for resolution; creates investigation report for fixer agent to guide implementation.
ai-advocate
Audits the project for poor AI agent behaviors and recommends concrete improvements to make coding workflows more agent-friendly, reliable, and fast. Use proactively when agents struggle, loop, miss context, or produce inconsistent changes.