A repeatable code-verification checklist for use after changes. It checks configured build commands, reviews the diff, and reports problems.

Checking features, bug fixes, refactors, and changes before a commit or pull request.

It reduces the chance of shipping regressions or untested changes by making verification part of the workflow.

bp-verify — Skill for Claude Code by kulmam92

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 kulmam92/cc-best-practices-marketplace --skill bp-verify

Clone the repo

git clone --depth 1 https://github.com/kulmam92/cc-best-practices-marketplace

Made for: Claude Code.

Or install cc-best-practices, the plugin that ships this one along with the rest of its 6 skills, 1 hook.

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/kulmam92/cc-best-practices-marketplace/bp-verify/github.svg)](https://agentmods.dev/skills/kulmam92/cc-best-practices-marketplace/bp-verify)

Your own site

<a href="https://agentmods.dev/skills/kulmam92/cc-best-practices-marketplace/bp-verify"><img src="https://agentmods.dev/badge/skills/kulmam92/cc-best-practices-marketplace/bp-verify/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/kulmam92/cc-best-practices-marketplace/bp-verify"><img src="https://agentmods.dev/badge/skills/kulmam92/cc-best-practices-marketplace/bp-verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 535 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	$0.00049	$0.00535
Opus 5	$0.00024	$0.00267
Sonnet 5	$0.00010	$0.00107
Haiku 4.5	$0.00005	$0.00053

Measured 11d ago against content hash fe0133d53fb9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

bp-verify 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 11d 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.

plugins/cc-best-practices/skills/bp-verify/SKILL.md · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verification Loop

Run this after every implementation step. Boris Cherny quantifies verification as improving quality by 2-3x.

Steps

Fail-safe check -- Read CLAUDE.md "Build & Validation Commands" section. If no commands are configured (section is empty or contains only comments):
- Scan for project config files and auto-detect available build commands
- Propose filling in the Build & Validation Commands section with the detected commands
- Wait for developer confirmation before updating CLAUDE.md
- If nothing is detected, tell the developer to configure commands manually or run /bp-setup
Run all configured commands -- Execute each command listed in the Build & Validation Commands section, in order. Report pass/fail with details on any failures.
Self-review the diff -- Read through all changed files. Check for:
- Regressions in existing functionality
- Missing error handling at system boundaries
- Inconsistencies with existing code patterns
- Hardcoded values that should be configurable
After each finding, evaluate: "Would this apply to OTHER code in this project, not just this diff?" If yes AND the same type of finding appears in 2+ files in the diff, append an inline rule suggestion directly below the finding:
```
- [Finding description]
  → /bp-learn "[concise rule text]"
```
Only suggest rules that are generalizable (applies beyond this diff), found in 2+ files, and not already captured in CLAUDE.md or .claude/rules/. If no findings qualify, show nothing extra.
Report results -- Present a clear pass/fail summary for each configured command, plus self-review findings (with inline suggestions where applicable).

If Something Fails

Fix the issue in the current chunk
If the fix is non-trivial, REVERT the chunk and rescope
Use Esc+Esc to rewind to a checkpoint, or git stash to revert file changes
Never layer patches on top of broken code
Trust the verification loop -- say "go fix it" rather than over-explaining the fix
If the same failure recurs after 2 attempts, /clear and restate the problem from scratch

Read the full file on GitHub · 45 lines

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.

11d ago First seen · 45 lines · 49 tokens per session scan A fe0133d53fb9

Subscribe to this mod's changes

bp-verify is a skill published in the GitHub repository kulmam92/cc-best-practices-marketplace (2 stars, last pushed 5mo ago), licensed MIT. It adds 49 tokens to every session and 535 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 2026-08-31.

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

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

bp-verify