engage.scorecard

engage.scorecard is a command for Claude Code from hypnguyen1209/offensive-claude. It costs 18 tokens per session (395 once invoked), scanned A, original, MIT.

A command for measuring how often an AI model's security decisions later prove wrong. It uses past outcomes to decide whether a type of decision can skip another review.

In plain words
What is it for?
Use it to record outcomes, inspect error rates and confidence limits, and check whether a model decision class is trusted.
Why use it?
It prevents the system from trusting new or unreliable decision patterns and keeps rechecking them until the evidence is sufficient.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the offensive-claude plugin — 30 skills, 18 commands, 8 agents, 1 hook shipped together

Good fit Use it to record outcomes, inspect error rates and confidence limits, and check whether a model decision class is trusted.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/hypnguyen1209/offensive-claude/engage.scorecard
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.

Clone the repo
git clone --depth 1 https://github.com/hypnguyen1209/offensive-claude

Made for: Claude Code.

Or install offensive-claude, the plugin that ships this one along with the rest of its 30 skills, 18 commands, 8 agents, 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.

agentmods badge for engage.scorecard

README.md
[![agentmods](https://agentmods.dev/badge/commands/hypnguyen1209/offensive-claude/engage.scorecard/github.svg)](https://agentmods.dev/commands/hypnguyen1209/offensive-claude/engage.scorecard)
Your own site
<a href="https://agentmods.dev/commands/hypnguyen1209/offensive-claude/engage.scorecard"><img src="https://agentmods.dev/badge/commands/hypnguyen1209/offensive-claude/engage.scorecard/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 engage.scorecard

Your own site · 80×15
<a href="https://agentmods.dev/commands/hypnguyen1209/offensive-claude/engage.scorecard"><img src="https://agentmods.dev/badge/commands/hypnguyen1209/offensive-claude/engage.scorecard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 395 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 $0.00018 $0.00395
Opus 5 $0.00009 $0.00198
Sonnet 5 $0.00004 $0.00079
Haiku 4.5 $0.00002 $0.00040

Measured 11d ago against content hash f56d15576d22, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

engage.scorecard 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.

commands/engage.scorecard.md · 32 lines

What it actually says

/engage.scorecard

Tracks how often a model's verdicts (finding-validator / finding-checker PASS/KILL/DOWNGRADE) were later overturned, and decides — fail-closed — when a (model, decision_class) cell is trustworthy enough to skip an expensive re-validation in the autopilot loop. Backed by engine/model_scorecard.py.

Usage

/engage.scorecard {record|rate|trusted|stats} ...

Process

  1. Record outcomes as you confirm them: model_scorecard.py record --model opus --class finding-validator:PASS --outcome correct|overturned (a "miss" = a verdict later overturned: a PASS that was a false positive, a KILL that was real).
  2. Consult before skipping a re-check (autopilot): model_scorecard.py trusted --model opus --class finding-validator:PASS → exit 0 trusted, 3 not. A cell is trusted ONLY when the Wilson 95% upper bound on its miss-rate ≤ 5% and there are enough samples (≈73+ clean) — fail-closed: a new/rarely-seen model or one recent miss is NOT trusted, so the autopilot keeps re-validating.
  3. Reviewmodel_scorecard.py stats shows per-(model, class) n / overturned / upper-bound / trusted.

Notes

  • Separate sqlite store ($MODEL_SCORECARD_DB), distinct from the JSONL engagement-memory pattern store.
  • This only ever adds a fast-path for well-proven cells; it never relaxes the proof bar — an untrusted cell simply gets the normal finding-validator + finding-checker treatment.
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. 11d ago First seen · 32 lines · 18 tokens per session scan A f56d15576d22

Subscribe to this mod's changes

engage.scorecard is a command published in the GitHub repository hypnguyen1209/offensive-claude (357 stars, last pushed 24d ago), licensed MIT. It adds 18 tokens to every session and 395 once invoked, about $0.0001 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.