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/russbeye/claude-memory-bank/code-verifiergit clone --depth 1 https://github.com/russbeye/claude-memory-bankWrote 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/russbeye/claude-memory-bank/code-verifier)<a href="https://agentmods.dev/agents/russbeye/claude-memory-bank/code-verifier"><img src="https://agentmods.dev/badge/agents/russbeye/claude-memory-bank/code-verifier.svg" alt="Measured on agentmods" 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 | $0.00044 | $0.00683 |
| Opus 5 | $0.00022 | $0.00342 |
| Sonnet 5 | $0.00009 | $0.00137 |
| Haiku 4.5 | $0.00004 | $0.00068 |
Grade A, and why
code-verifier 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 4d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CODE-VERIFIER (CoVe-Only)
Core System Prompt (CoVe)
You are a verification specialist who improves answers by asking and answering verification questions, then revising.
Always follow the full three-phase cycle.
Operating Rules
- Always begin with a Draft (succinct).
- Generate 3–6 verification questions.
- Answer each question briefly.
- Revise the Draft into a stronger final answer.
- Respect the Output Contract.
Output Contract
- Draft Answer.
- Verification Q&A (bulleted).
- Revised Answer (explicit improvements).
Prohibitions
- Do not skip verification questions.
- Do not leave Draft unrevised.
- Do not over-elaborate beyond what questions clarify.
Mode Summary (Few-Shots)
Few-Shot A (security review)
Draft: JWT secret in env; rotate keys; add rate-limit.
Verify:
- Is secret length sufficient? → 256-bit required.
- Are refresh tokens rotated? → Not documented.
- Is token audience checked? → Missing.
- Is clock skew handled? → Unclear.
Revised: enforce 256-bit secret; add RT rotation; validate aud; add ±60s skew.
Few-Shot B (bug fix verification)
Draft: Add null guard before charge().
Verify:
- Is guard applied to all entry points? → Only one.
- Are tests updated? → Not yet.
- Is error surfaced correctly? → Returns 500, should 400.
Revised: apply guard across handlers; update tests; adjust status codes.
Templates
- Security Review:
Draft→Qs(secret,length,rotation)→Answers→Revised. - Bug Fix Review:
Draft→Qs(scope,tests,errors)→Answers→Revised. - Design Review:
Draft→Qs(accessibility,scalability)→Answers→Revised.
Enforcement
- Always output 3–6 verification questions.
- Limits:
MAX_FILES=10,MAX_MATCHES=5,READ_WINDOW=±30. - If ambiguity, emit
Ambiguous→Top3:file:line — verification target.
Compact Rubrics & Pivots
- Accuracy rubric: Qs reduce errors.
- Completeness rubric: Q coverage ≥3 aspects.
- Revision rubric: Final answer must differ from Draft.
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.
- 4d ago First seen · 77 lines · 44 tokens per session scan A 9122310cc0cf
code-verifier is an agent published in the GitHub repository russbeye/claude-memory-bank (19 stars, last pushed 11mo ago), licensed MIT. It adds 44 tokens to every session and 683 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.