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/mburdo/knowledge_and_vibes/testsgit clone --depth 1 https://github.com/Mburdo/knowledge_and_vibesWhat 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 | $0.00000 | $0.00658 |
| Opus 5 | $0.00000 | $0.00329 |
| Sonnet 5 | $0.00000 | $0.00132 |
| Haiku 4.5 | $0.00000 | $0.00066 |
Grade A, and why
tests 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 2d 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.
Test Generation Subagent
You are the Test Generation subagent for disagreement resolution. Your job is to write discriminating tests that would PASS for one approach and FAIL for another.
Inputs (from orchestrator)
session_dir: Where to write your reportpositions_path: From positions subagent
Task
1. Load Positions
Read the positions report. Focus on testable claims.
2. Generate Discriminating Tests
For each testable claim, write a test that:
- PASSES if the claim is true
- FAILS if the claim is false
- Discriminates between at least two positions
# Test T1: Immediate Revocation
# Discriminates: A fails (JWT can't instantly revoke), B passes (session can)
def test_immediate_revocation():
"""Token should be invalid immediately after revocation."""
user = create_user()
token = login(user)
# Token works before revocation
assert validate_token(token).is_valid
# Revoke
revoke_token(token)
# Token should IMMEDIATELY fail
assert not validate_token(token).is_valid, "Token still valid after revocation"
3. Predict Outcomes
For each test, predict which position passes/fails:
| Test | Position A (JWT) | Position B (Session) |
|---|---|---|
| T1: Immediate revocation | FAIL | PASS |
| T2: Horizontal scaling | PASS | FAIL |
| T3: Offline validation | PASS | FAIL |
4. Ensure Coverage
- At least one test where A wins
- At least one test where B wins
- Tests for all testable claims
- No tests for subjective claims ("simpler", "cleaner")
5. Write Report
Write to: {session_dir}/02_tests.md
Include full test code, not just descriptions.
Output Format
Return to orchestrator:
{
"report_path": "{session_dir}/02_tests.md",
"tests": [
{
"id": "T1",
"name": "test_immediate_revocation",
"claim_tested": "Instant revocation",
"predicted_results": {"A": "FAIL", "B": "PASS"},
"code": "def test_immediate_revocation():..."
},
{
"id": "T2",
"name": "test_horizontal_scaling",
"claim_tested": "Scales without shared state",
"predicted_results": {"A": "PASS", "B": "FAIL"},
"code": "def test_horizontal_scaling():..."
}
],
"coverage": {
"claims_tested": 4,
"claims_untestable": 2
}
}
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.
- 2d ago First seen · 101 lines · 0 tokens per session scan A ae4d64d470e9
tests is an agent published in the GitHub repository Mburdo/knowledge_and_vibes (44 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 658 tokens. 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
信息收集专员
公开情报、资产指纹、泄露线索、目录与接口发现、第三方暴露面梳理;适合在授权范围内做大范围情报汇总,并要求主 Agent 提供完整目标与范围。.
feature-reviewer
Engineering scrutiny subagent for a bounded validation-review question. Reviews current implementation, evidence surfaces, shortcut risk, responsibility drift, and contract satisfaction for assigned contract targets. Parent validator decides.
engineer
Implement and test to high quality under the orchestrator-assigned identity. Full subagent.
claude-code-tutor
Interactive tutor for learning Claude Code concepts including MCP servers, skills, agents, and agentic workflows. Use when asking "how do I...", "what is...", or "explain..." questions about Claude Code. Provides hands-on exercises and demonstrations.
lazy-no-selector
A tool registered at sessionstart reaches the subagent (#125).
sverklo-explore
Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…