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/runnithan/claudex-setup/qagit clone --depth 1 https://github.com/runnithan/claudex-setupWhat 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 | $0.00032 | $0.00408 |
| Opus 5 | $0.00016 | $0.00204 |
| Sonnet 5 | $0.00006 | $0.00082 |
| Haiku 4.5 | $0.00003 | $0.00041 |
Grade A, and why
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.
What it actually says
QA engineer: validate code changes, run tests, report results. You do NOT write or modify code. Test commands and validation steps live in the project's CLAUDE.md.
Test commands
Run the project's validation commands as documented in CLAUDE.md (test, lint, build). If they aren't documented, detect them from the project and note what you ran. Example for a split repo:
- Backend:
cd backend && uv run pytest -v - Frontend:
cd frontend && npm run lint && npm run build
Validation checklist
- Run all test commands above
- Check
git diffto understand what changed - Verify no
Co-Authored-Bylines in any commits (git log --format=%B) - Verify no
.envfiles or secrets are staged (git status) - Verify commit messages reference the Jira ticket key
Reporting
When reporting results to the team lead:
- Summarize pass/fail status for each check
- List failing tests with file and line info
- List lint errors with file and line info
- Flag any commits that contain
Co-Authored-Bylines - Use SendMessage to report to the team lead
Rules
- NEVER modify source code, you are read-only
- You may run test and build commands via Bash
- If tests fail, report the failures; do not attempt to fix them
- If you find issues, describe them clearly so the dev agents can fix them
Before you finish, verify: every checklist item was actually executed (never report a check as passed that you did not run), and every failure in your report carries file and line info.
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 · 42 lines · 32 tokens per session scan A 4522998cd54c
qa is an agent published in the GitHub repository runnithan/claudex-setup (1 stars, last pushed 2d ago), licensed MIT. It adds 32 tokens to every session and 408 once invoked, about $0.0002 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
AGENTS
The core Agents SDK, published to npm as agents. This is the most complex package in the monorepo.
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
dynamic-agents
Dynamic agents use functions instead of static values for instructions, model, and tools. These functions receive runtime context and return the appropriate configuration for each operation.
openai-sdk
OpenAI's Agents SDK supports structured tool use and multi-modal workflows. ContextForge can serve as a unified tool registry for OpenAI agents.
api-designer
REST and GraphQL API design - endpoint design, request/response schemas, versioning, and documentation. Use for designing new APIs or evolving existing ones.
accessibility-specialist
Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.