What is verify-bukku?

A project-specific verification tool for the Bukku command-line app and its MCP server, which lets an AI client use tools through standard input and output. It runs commands in a throwaway home folder and records their output and exit codes.

Use it to build the packages, launch each interface, test configuration and error handling, and save command transcripts for review. With credentials, it can also check read-only calls against a Bukku test company.

It provides evidence that the two interfaces behave as a user would expect without changing the developer's real configuration. It can work offline for validation and startup checks, while read-only API checks require Bukku test credentials.

How centry-digital/bukku configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to centry-digital/bukku. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/centry-digital/bukku/main/.claude/skills/verify-bukku/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/centry-digital/bukku

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/centry-digital/bukku/verify-bukku/github.svg)](https://agentmods.dev/skills/centry-digital/bukku/verify-bukku)

Your own site

<a href="https://agentmods.dev/skills/centry-digital/bukku/verify-bukku"><img src="https://agentmods.dev/badge/skills/centry-digital/bukku/verify-bukku/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/centry-digital/bukku/verify-bukku"><img src="https://agentmods.dev/badge/skills/centry-digital/bukku/verify-bukku.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 111 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,746 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.

Model	Per session	Once invoked
Fable 5.1	$0.00111	$0.01746
Opus 5.5	$0.00044	$0.00698
Sonnet 5.5	$0.00022	$0.00349
Haiku 4.5	$0.00011	$0.00175

Measured 7d ago against content hash cd77b6bf0bcb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

verify-bukku 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 7d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/mcp-call.mjs, scripts/verify.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.

.claude/skills/verify-bukku/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify bukku

The product has two surfaces, both thin layers over packages/core and the Bukku REST API at https://api.bukku.my (hard-coded, no local stand-in):

CLI bukku (packages/cli, published as @centry-digital/bukku-cli). Short-lived: one process per command, JSON on stdout, a JSON error and a non-zero exit code on failure. Credentials come from --api-token/--company-subdomain, then BUKKU_API_TOKEN/BUKKU_COMPANY_SUBDOMAIN, then ~/.bukkurc.
MCP server bukku-mcp (packages/mcp, published as @centry-digital/bukku-mcp). Spoken to over stdio by an AI client. It needs both env vars and calls the API to validate the token before it lists any tools, so without real credentials only its startup error can be driven.

All helpers live in .claude/skills/verify-bukku/scripts/. Run them from the repo root. Below, V=.claude/skills/verify-bukku.

Launch

Prerequisites: Node 22 (.nvmrc), npm ci done.

$V/scripts/verify.sh launch

Runs npm run build, creates a run id, an evidence folder .verify/evidence/<run id>/ and a sandbox .verify/run/<run id>/ holding a throwaway HOME (so ~/.bukkurc is never the user's) and TMPDIR.
Ready when it prints ready. The run id is saved in .verify/run/current; every other command uses it (or VERIFY_RUN_ID if set).
There is no server to keep alive: each cli or mcp drive below is its own process. Runs don't share state, but only one run is "current" per checkout.

Live mode. By default every drive runs with no Bukku credentials in its environment. For a live drive, export BUKKU_API_TOKEN and BUKKU_COMPANY_SUBDOMAIN for a test company (never a client's books) and set VERIFY_LIVE=1. Even then the harness refuses any CLI write that lacks --dry-run and any MCP tool other than list-*, get-* and search-*, unless VERIFY_ALLOW_WRITES=1 is also set. Set that only when the repo owner has approved writes to that test company for this run. In live mode any HTTPS_PROXY, NO_PROXY and NODE_EXTRA_CA_CERTS are passed through to drives (with NODE_USE_ENV_PROXY=1, which Node's fetch needs to use a proxy).

Read the full file on GitHub · 88 lines

Files

What ships with it

10 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.

7d ago First seen · 88 lines · 111 tokens per session scan A cd77b6bf0bcb

Subscribe to this mod's changes

verify-bukku is a skill published in the GitHub repository centry-digital/bukku (9 stars, last pushed 4d ago), licensed MIT. It adds 111 tokens to every session and 1,746 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-22.

Testing

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

cua-driver

Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.

davidondrej/skills · 68 tokens

bukku: Skill for Claude Code