scorecard

scorecard is a command for coding agents from brainOS-HQ/brain-os. It costs 0 tokens per session (969 once invoked), scanned A, original, MIT.

A command for running a repeatable weekly health check of Brain OS, scoring it out of 100 and comparing the result with the previous week.

In plain words
What is it for?
Use it to check a project or all projects, review overdue items and contradictions, examine feedback, detect patterns, and track changes week over week.
Why use it?
It turns several checks about memory, decisions, user feedback, and working patterns into one consistent review.

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/brainos-hq/brain-os/scorecard
Clone the repo
git clone --depth 1 https://github.com/brainOS-HQ/brain-os

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 scorecard

README.md
[![agentmods](https://agentmods.dev/badge/commands/brainos-hq/brain-os/scorecard.svg)](https://agentmods.dev/commands/brainos-hq/brain-os/scorecard)
Your own site
<a href="https://agentmods.dev/commands/brainos-hq/brain-os/scorecard"><img src="https://agentmods.dev/badge/commands/brainos-hq/brain-os/scorecard.svg" alt="Measured on agentmods" 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 969 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 5.1 $0.00000 $0.00969
Opus 5 $0.00000 $0.00485
Sonnet 5 $0.00000 $0.00194
Haiku 4.5 $0.00000 $0.00097

Measured 5d ago against content hash 8d962ae29606, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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 5d 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.

templates/commands/scorecard.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Brain OS : Weekly Scorecard

Run a repeatable weekly health check. Score Brain OS out of 100. Compare week-over-week.

Arguments

$ARGUMENTS — optional entity scope (default: my-project). Pass all to score globally.

Tool sequence

Run all five reads first, then score:

  1. mcp__brain-os__entity_read(entity_id="my-project") — momentum, mode, staleness
  2. mcp__brain-os__memory_check(entity_id="my-project") — overdue reviews, contradiction signals
  3. mcp__brain-os__decision_review(entity_id="my-project", root_path="<cwd>") — overdue decisions, placeholder proof actions
  4. mcp__brain-os__semantic_recall("tester feedback onboarding first-session value Brain OS", max_results=5) — user signal
  5. mcp__brain-os__pattern_detect(scope="recent") — active patterns, shipping vs. self-correction balance

Scoring rubric (100 points)

1. Memory Hygiene — 20 pts

Score Condition
20 No contradictions; my-project overdue reviews = 0; global overdue trending down; no placeholder proof actions
15 No contradictions; my-project overdue reviews 1–3
10 No contradictions; overdue reviews accumulating
0–5 Contradictions present or obvious stale/unsafe state

2. Reasoning Quality — 20 pts

Score Condition
20 Decisions have why, assumptions, invalidate_if, real proof_action; review-trigger behavior working
15 Mostly strong; some placeholder or duplicate decisions remain
10 Works but inconsistent or noisy
0–5 Decisions vague, non-testable, or hard to trust

3. Reliability / Trust — 20 pts

Score Condition
20 Tests green; no corruption bugs active; audit clean; no dangerous memory signals
15 Mostly stable; minor rough edges
10 Recurring tool bugs or trust breaks
0–5 Users cannot trust outputs

4. Actionability — 15 pts

Score Condition
15 Clear next move; usable focus/reconcile output; system helps user decide what to do now
10 Useful but requires manual interpretation
5 Smart but not operationally helpful

Read the full file on GitHub · 100 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. 5d ago First seen · 100 lines · 0 tokens per session scan A 8d962ae29606

Subscribe to this mod's changes

scorecard is a command published in the GitHub repository brainOS-HQ/brain-os (6 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 969 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 2026-08-31.