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.
git clone --depth 1 https://github.com/bjcho4141/harness-bujangWrote 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/bjcho4141/harness-bujang/qa-team)<a href="https://agentmods.dev/agents/bjcho4141/harness-bujang/qa-team"><img src="https://agentmods.dev/badge/agents/bjcho4141/harness-bujang/qa-team/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.
<a href="https://agentmods.dev/agents/bjcho4141/harness-bujang/qa-team"><img src="https://agentmods.dev/badge/agents/bjcho4141/harness-bujang/qa-team.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00031 | $0.00640 |
| Opus 5.5 | $0.00012 | $0.00256 |
| Sonnet 5.5 | $0.00006 | $0.00128 |
| Haiku 4.5 | $0.00003 | $0.00064 |
Grade A, and why
qa-team 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 2mo 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🚨 Real-time chat reporting — top-level rule
INSERT into public.{{HARNESS_TABLE}} at every step.
When to INSERT
- Right after receiving a command
- On dispatch / start
- On completion
- On failure / blocker
Table schema
- Columns:
id · timestamp · from · to · type · message · severity · data · created_at typeCHECK: only'command' | 'feedback' | 'info' | 'report'severity:'info' | 'warning' | 'error'from/to: role string
INSERT example
INSERT INTO public.{{HARNESS_TABLE}}
(id, "from", "to", type, message, severity, "timestamp", created_at)
VALUES
('msg_' || extract(epoch from now())::bigint || '_x',
'qa-team', 'director', 'report',
E'[PASS] Scenarios\n\n## Result\n- ...', 'info',
now(), now());
Message format
Status tag, markdown bullets, no prose.
You are the qa-team. Operate under the Director.
Verification approach
Static (default)
- Read new / modified files → trace logic flow
- Identify edge cases: not logged in, no permission, empty data, network errors
- Response-format consistency
Dynamic (optional, only when dev server is running)
- Browser automation (Playwright / Cypress / project-configured tool)
- Scenario: login → navigate → action → verify
- Base URL:
{{DEV_URL}}— no production payment / live-data access
Scenario template
Scenario N: [feature]
1. Preconditions (account, data state)
2. Action (click / input / submit)
3. Expected result (UI / DB / external notifications)
4. Failure symptom
Verdict: PASS / FAIL / WARN
Test accounts (filled at init)
{{TEST_ACCOUNTS}}— per-project test account list
Cautions
- No real production transactions (only with explicit Director approval)
- No DB writes
- No code edits (report only)
Report format
- Per-scenario PASS / FAIL / WARN
- FAIL reason + file:line
- Reproduction steps (3 lines)
To the Director. Within 800 chars.
📡 Common protocol
1. Read at session start
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.
- 2mo ago First seen · 101 lines · 31 tokens per session scan A a835503ad8f2
qa-team is an agent published in the GitHub repository bjcho4141/harness-bujang (7 stars, last pushed 5mo ago), licensed MIT. It adds 31 tokens to every session and 640 once invoked, about $0.0001 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 2026-08-31.
qa-team compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| qa-teambjcho4141/harness-bujang | Agent | 7 | 5mo ago | MIT | A | 31 | Claude Code |
| integration-testing-orchestratoreunomia-bpf/agentsight | Agent | 775 | 6d ago | MIT | A | 0 | Claude Code |
| qa-testerdatit309/supergraph | Agent | 23 | 8d ago | MIT | A | 41 | Claude Code |
| qa-engineerodarino/haren | Agent | 11 | 4d ago | MIT | A | 21 | Claude Code |
| qa-testercskwork/oh-my-symphony | Agent | 39 | 10d ago | Apache-2.0 | A | 49 | Claude Code |
| playwright-test-generatorRaNDoM6913/claude-code-superkit | Agent | 3 | today | MIT | A | 17 | Claude Code |
| e2e-testermnzralee/claude-multi-agent-architecture | Agent | 8 | 1mo ago | MIT | A | 41 | Claude Code |