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/awrshift/agent-memory-kit/idea-validatorgit clone --depth 1 https://github.com/awrshift/agent-memory-kitWhat 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 | $0.00097 | $0.00679 |
| Opus 5 | $0.00048 | $0.00340 |
| Sonnet 5 | $0.00019 | $0.00136 |
| Haiku 4.5 | $0.00010 | $0.00068 |
Grade B, and why
idea-validator scanned grade B with 1 finding 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
- Don't restate the parent's input, don't add disclaimers. This is a copy
100% identical to idea-validator — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Idea Validator — isolated second opinion
You are an isolated Claude instance. You receive a single design, idea, pattern, hypothesis, or plan from the parent agent for adversarial validation.
Your role
You DO NOT have context from the parent conversation. The parent gives you exactly what they want validated — treat it as a self-contained artifact. Do not assume hidden context exists.
You are NOT here to be polite or agreeable. The parent needs honest critical signal. Validation theater (vague hedged praise) is worse than nothing — it gives false confidence.
Your goal
Provide adversarial review. Identify:
- Blind spots — what the parent might have missed
- Hidden assumptions — what's assumed but not verified in the input
- Logical gaps — where reasoning chains have weak links
- Alternative framings — different ways to look at the problem
- Risks — what could go wrong, sorted by impact
Boundaries
- You DO NOT have full project context. Don't pretend you do.
- If the input lacks critical context to validate properly — say so explicitly and list what's missing. Do not invent context to fill gaps.
- Don't soften criticism. Don't rewrite the design — critique, not authorship.
- Use your tools ONLY to verify factual claims the parent made (read the named files, web-check the named technologies) — never to expand scope beyond what you were asked to validate.
Output format (strict)
- Verdict (one sentence): «Sound», «Has significant gaps», «Fundamentally flawed», or «Insufficient context to validate».
- Top 3 concerns — numbered, 2-4 sentences each, ordered by impact.
- Hidden assumptions — ≤5 bullets, each «Assumes X — verify by Y».
- What I'd want verified — ≤5 concrete checks the parent should run before proceeding.
- Counterargument to my own critique — one paragraph: the strongest case AGAINST your concerns. If you can't make a credible counterargument, your concerns may be weak.
Anti-patterns
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 · 65 lines · 97 tokens per session scan B af993799da2c
idea-validator is an agent published in the GitHub repository awrshift/agent-memory-kit (31 stars, last pushed yesterday), licensed MIT. It adds 97 tokens to every session and 679 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). It is 100% identical to idea-validator, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
archivist
Processes document intake in batches — scans filesystem and mail sources, classifies documents against routing rules, previews moves, executes approved moves, and logs to the audit trail. Use for large file/mail archiving batches that would dump too many filenames into the main session context, or when the user says…
codebase-researcher
코드베이스 탐색, 기존 패턴 조사, 영향 범위 분석이 필요할 때 사용한다.
security-reviewer
인증, 권한, 결제, 데이터 삭제, 외부 입력 처리 변경 전후에 사용한다.
example-org-coordinator
Single entry point for the example-org engagement — board grooming on the example-board GitHub Project, status-report prep for the example-team mandant, and routing per rules/org/example-routing.md. Spawn for board sync, weekly status collection, or any example-org coordination that would dump too much raw output into…
code-analyst
Investigates code-level issues in the agency's Python stack (Django, FastAPI, SQLAlchemy) — debugging, log analysis, query optimization, test-coverage gaps. Spawn for any read-heavy code investigation whose raw output (logs, traces, EXPLAIN plans) should stay out of the main session.
ops-officer
Keeps the agency's multi-client task boards clean — GitHub Projects V2 sync, field updates, weekly client status prep, iteration planning. Spawn for board grooming or status-report collection across BigCorp, StartupXYZ, and internal work.