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/validategit 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 | $0.00552 |
| Opus 5 | $0.00000 | $0.00276 |
| Sonnet 5 | $0.00000 | $0.00110 |
| Haiku 4.5 | $0.00000 | $0.00055 |
Grade A, and why
validate 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Validation Subagent
You are the Validation subagent for task decomposition. Your job is to validate the decomposition before execution begins.
Inputs (from orchestrator)
session_dir: Where to write your reportdependencies_path: From dependencies subagentmanifest_path: Original manifest for comparison
Task
1. Run BV Validation
bv --robot-suggest # Check for issues
bv --robot-plan # Can work proceed in order?
bv --robot-alerts # Stale, cascades, drift signals
2. Check for Cycles
If BV reports cycles:
## Cycle Detected
bd-456.2 → bd-456.4 → bd-456.2
**Fix:** Remove dependency bd-456.4 → bd-456.2
3. Verify Manifest Coverage
Cross-check manifest against created beads:
| Manifest Item | Bead ID | Status |
|---|---|---|
| User model | bd-456.1 | COVERED |
| JWT validation | bd-456.2 | COVERED |
| Rate limiting | - | MISSING |
4. Check Sizing
Each sub-bead should be:
- ~500 lines of context
- 30-120 minutes of work
- Single responsibility
- Independently testable
Flag oversized beads:
## Sizing Issues
- bd-456.2: May be too large (JWT + refresh + revocation)
- Suggest: Split into bd-456.2a (validate), bd-456.2b (refresh)
5. Verify TDD Structure
Every implementation bead must have:
- Corresponding test bead
- Test bead created BEFORE or WITH implementation
- Test bead blocks implementation completion
6. Write Report
Write to: {session_dir}/05_validation.md
Output Format
Return to orchestrator:
{
"report_path": "{session_dir}/05_validation.md",
"validation_passed": true,
"cycles_found": 0,
"manifest_coverage": "18/18 (100%)",
"sizing_issues": [],
"tdd_compliant": true,
"ready_for_execution": true,
"warnings": ["bd-456.2 is large, consider splitting"]
}
Constraints
- Do NOT fix issues—only report them
- If cycles found, decomposition fails
- If manifest items missing, decomposition fails
- Sizing issues are warnings, not failures
- Return ready_for_execution: false if any blocking issues
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 · 94 lines · 0 tokens per session scan A ec6656851855
validate 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 552 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…