scorecard

A command that displays historical evaluation scores and trends for skills. It can show all skills or filter the results to one skill and a chosen number of recent evaluations.

In plain words
What is it for?
Use it to review score history, filter by skill name, limit results with --last, or display all available evaluations with --all.
Why use it?
It helps you see whether a skill’s evaluation results are improving, declining, or staying similar over time.

Command

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.

agentmods
npx agentmods add commands/sattyamjjain/proofloop/scorecard
Clone the repo
git clone --depth 1 https://github.com/sattyamjjain/proofloop
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 616 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00010 $0.00616
Opus 5 $0.00005 $0.00308
Sonnet 5 $0.00002 $0.00123
Haiku 4.5 $0.00001 $0.00062

Measured 2d ago against content hash 03df7ac6f29f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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/scorecard.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Display historical scores for skills that have been evaluated by Proofloop.

Arguments

  • skill-name (optional): Filter to a specific skill. If omitted, show all skills.
  • --last N (optional): Show only the last N evaluations. Default: 10.
  • --all (optional): Show all evaluations regardless of limit.

What to Do

  1. Read score files from skills/judge/scores/ directory
  2. Parse each JSON score file
  3. Filter by skill name if provided
  4. Sort by timestamp (newest first)
  5. Limit to last N if specified
  6. Display formatted table:
┌─────────────────────────────────────────────────────────────┐
│  PROOFLOOP SCORE HISTORY                                   │
├──────────────┬───────┬───────┬────────────┬────────────────┤
│ Skill        │ Score │ Grade │ Date       │ Trend          │
├──────────────┼───────┼───────┼────────────┼────────────────┤
│ code-review  │ 8.2   │ B+    │ 2026-02-13 │ ↑ (+0.4)       │
│ code-review  │ 7.8   │ B     │ 2026-02-12 │ → (+0.0)       │
│ security-scan│ 9.1   │ A     │ 2026-02-13 │ ↑ (+0.6)       │
├──────────────┼───────┼───────┼────────────┼────────────────┤
│ AVERAGES     │ 8.37  │ B+    │            │                │
└──────────────┴───────┴───────┴────────────┴────────────────┘
  1. Calculate trends:

    • Compare each score to the previous score for the same skill
    • ↑ = improved by 0.3+
    • ↓ = declined by 0.3+
    • → = stable (within 0.3)
  2. Show averages per skill and overall

If no scores exist yet, inform the user: "No scores found. Run /judge after a skill execution to start building history."

  • /against — side-by-side delta between two specific runs of the same skill.
  • /benchmark — delta between a skill's historical average and the reference standards in skills/judge/references/benchmark-standards.md.
  • python3 skills/judge/scripts/studio.py --scores-dir skills/judge/scores --output proofloop-studio.html — self-contained HTML dashboard with per-skill radar charts.

Read the full file on GitHub · 56 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.

  1. 2d ago First seen · 56 lines · 10 tokens per session scan A 03df7ac6f29f

Subscribe to this mod's changes

scorecard is a command published in the GitHub repository sattyamjjain/proofloop (5 stars, last pushed 2mo ago), licensed MIT. It adds 10 tokens to every session and 616 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 2026-08-31.