CLAUDE-CERTIFICATIONS: Command for Claude Code

.claude/commands/cert/score-check.md

score-check is a command for Claude Code from Amey-Thakur/CLAUDE-CERTIFICATIONS. It costs 0 tokens per session (444 once invoked), scanned A, original, MIT.

A command that reviews certification practice results and gives a recommendation about booking the exam, studying more, or retaking the test. It considers both the overall result and performance in each exam subject area.

In plain words
What is it for?
Use it with a Pearson score report, earlier mock or diagnostic results, or an informal self-assessment.
Why use it?
It turns score data into a study decision, so you can focus on weak subjects that matter most to the exam instead of relying only on the total score.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

This is Amey-Thakur/CLAUDE-CERTIFICATIONS's own configuration. It tells Claude Code how to work on CLAUDE-CERTIFICATIONS itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything CLAUDE-CERTIFICATIONS configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Amey-Thakur/CLAUDE-CERTIFICATIONS. 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/Amey-Thakur/CLAUDE-CERTIFICATIONS/main/.claude/commands/cert/score-check.md
Clone the repo
git clone --depth 1 https://github.com/Amey-Thakur/CLAUDE-CERTIFICATIONS

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.

agentmods badge for score-check

README.md
[![agentmods](https://agentmods.dev/badge/commands/amey-thakur/claude-certifications/score-check/github.svg)](https://agentmods.dev/commands/amey-thakur/claude-certifications/score-check)
Your own site
<a href="https://agentmods.dev/commands/amey-thakur/claude-certifications/score-check"><img src="https://agentmods.dev/badge/commands/amey-thakur/claude-certifications/score-check/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 score-check

Your own site · 80×15
<a href="https://agentmods.dev/commands/amey-thakur/claude-certifications/score-check"><img src="https://agentmods.dev/badge/commands/amey-thakur/claude-certifications/score-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 444 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 $0.00000 $0.00444
Opus 5 $0.00000 $0.00222
Sonnet 5 $0.00000 $0.00089
Haiku 4.5 $0.00000 $0.00044

Measured 10d ago against content hash 8f05634674fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

score-check 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 10d 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.

.claude/commands/cert/score-check.md · 27 lines

What it actually says

Interpret the results in $ARGUMENTS and give a decision, not just a summary.

Input

Accept any of these: a real Pearson score report with its scaled score and percent-correct by domain, results from /cert:mock or /cert:diagnostic earlier in this session, or informal self-assessment. Ask for the certification if it was not named. If only an overall number was given, ask whether a per-domain breakdown exists, since the decision depends on where the marks were lost, not only how many.

Analyse

  1. Read the certification's README.md for domain weights and mock-exam-1.md for the readiness bands.
  2. For each domain, compute the gap between the score and a passing standard, then weight that gap by the domain's share of the exam. Rank by the weighted gap: a weak domain worth 33% of the paper matters far more than a weak domain worth 3%.
  3. Note any domain that is strong, so time is not wasted there.

Decide

Give one of three verdicts, with the reasoning shown:

  • Book it. Scores are comfortably above the band and no heavily weighted domain is weak.
  • Close the gap first. Name the specific domains and objectives, estimate the study time from the size of the weighted gaps, and recommend /cert:drill on each in priority order followed by /cert:mock.
  • Rebuild the foundation. Several heavy domains are weak. Recommend /cert:prep-plan and the underlying courses rather than more question practice, since drilling cannot fix material never learned.

For a real failed attempt, add the retake facts from guide/policies.md: the waiting period for that attempt number, the four-attempts-per-year limit, and that the fee applies again. Point out that the official score report's per-domain percentages are the most reliable study signal available, and should drive the next plan.

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. 10d ago First seen · 27 lines · 0 tokens per session scan A 8f05634674fe

Subscribe to this mod's changes

score-check is a command published in the GitHub repository Amey-Thakur/CLAUDE-CERTIFICATIONS (21 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 444 tokens. 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.