bank-gate

bank-gate is a skill for Claude Code, Codex from dudarenok-maker/executive-application-helper. It costs 196 tokens per session (2,051 once invoked), scanned A, original, MIT.

A session-closing verification check for projects that use evidence-bank files, MatrixRows, project instructions, or changelogs. It combines several repository and consistency checks into one report.

In plain words
What is it for?
Use it at the end of a session that changed the covered files to check commit discipline, file coherence, cross-references, and personal-context handling.
Why use it?
It catches problems that ordinary version control may miss, such as stale file views or references to watch-outs that do not exist.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it at the end of a session that changed the covered files to check commit discipline, file coherence, cross-references, and personal-context handling.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dudarenok-maker/executive-application-helper/bank-gate
Install

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.

Any agent
npx skills add dudarenok-maker/executive-application-helper --skill bank-gate
Clone the repo
git clone --depth 1 https://github.com/dudarenok-maker/executive-application-helper

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for bank-gate

README.md
[![agentmods](https://agentmods.dev/badge/skills/dudarenok-maker/executive-application-helper/bank-gate/github.svg)](https://agentmods.dev/skills/dudarenok-maker/executive-application-helper/bank-gate)
Your own site
<a href="https://agentmods.dev/skills/dudarenok-maker/executive-application-helper/bank-gate"><img src="https://agentmods.dev/badge/skills/dudarenok-maker/executive-application-helper/bank-gate/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.

agentmods 80×15 button for bank-gate

Your own site · 80×15
<a href="https://agentmods.dev/skills/dudarenok-maker/executive-application-helper/bank-gate"><img src="https://agentmods.dev/badge/skills/dudarenok-maker/executive-application-helper/bank-gate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 196 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,051 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00196 $0.02051
Opus 5 $0.00098 $0.01026
Sonnet 5 $0.00039 $0.00410
Haiku 4.5 $0.00020 $0.00205

Measured 9d ago against content hash d16eb92cbcac, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

bank-gate 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 9d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (references/check-script.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

template/skills/bank-gate/SKILL.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bank Gate — consolidated session-close verification skill

Setup note: This is a template skeleton. Set the workspace path at the top of references/check-script.sh, and replace [Candidate Name] / [Candidate First Name] / [Workspace Folder Path] throughout. The gate assumes the workspace is a git repository — if git init has not been run, do that first (see the project instructions, Git discipline).

One invocation, four checks, one report. This gate replaces the retired integrity stack (snapshot-check, bank-integrity-check, personal-context-discretion-check) under the git-based safety model.

Two of the three retired skills were made redundant by git: snapshots and end-of-file / line-count integrity axes are both answered better by git diff and git checkout than by a folder of dated copies. Two things git does not solve survive into this gate: a semantic cross-reference (a matrix row naming a watch-out sub-variant that does not exist) is a perfectly valid commit, and a mount-cache incoherence can hand the shell a stale view of a file that a later rewrite then persists as a truncation. Those are Checks 3 and 2.

MANDATORY — emit the verification checklist table

This gate is not run until its checklist is written down. Load references/checklist.md and emit that table in full: one row per item, each with an explicit verdict and the evidence that produced it. A row that cannot be evidenced is UNVERIFIED, and UNVERIFIED is treated as a FAIL.

Required row count — 7 + 2F + N:

Block Rows
Check 1 — git commit discipline 3 (rows 1.1–1.3)
Check 2 — mount-cache coherence 2 × F (F = bank / changelog files changed this session; two rows per file)
Check 3 — watch-out cross-references N (one row per distinct reference found; if none, one row recording the command and its empty output)
Check 4 — personal-context discretion 4 (rows 4.1–4.4) — emitted every session, N-A with a reason where nothing sensitive surfaced

Read the full file on GitHub · 122 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 9d ago First seen · 122 lines · 196 tokens per session scan A d16eb92cbcac

Subscribe to this mod's changes

bank-gate is a skill published in the GitHub repository dudarenok-maker/executive-application-helper (2 stars, last pushed 21d ago), licensed MIT. It adds 196 tokens to every session and 2,051 once invoked, about $0.0010 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 2026-08-31.