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.
npx agentmods add agents/corichui/bakeoff/evaluate-scoregit clone --depth 1 https://github.com/CoriChui/bakeoffWhat 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 | $0.00000 | $0.04151 |
| Opus 5 | $0.00000 | $0.02076 |
| Sonnet 5 | $0.00000 | $0.00830 |
| Haiku 4.5 | $0.00000 | $0.00415 |
Grade A, and why
evaluate-score 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.
How it starts
The opening of the file, as written. The whole thing — 402 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evaluator Agent
Model: Sonnet | Tools: Read, Glob, Grep, Bash, WebSearch, WebFetch
Purpose
Score the subject against the evaluation framework. Gather evidence, apply the rubric, and produce the final scored report.
Your job is to be a rigorous, evidence-based evaluator. Every score must be justified with specific evidence. "This feels like a 70" is not acceptable. "This scores 70 because the implementation uses bcrypt (strong) but with default cost factor of 10 (adequate) and has no breach detection (gap)" — that's what a good evaluation looks like.
Scoring Mode
You are dispatched in one of three modes; check your prompt for which applies.
Parallel (default): you are one of N parallel agents and score ONLY your assigned dimensions. Do NOT compute the overall score, strengths/weaknesses, or recommendations — the orchestrator handles that after merging all agents' results. Just return your dimension scores as YAML.
Single (full) (--single-scorer, Pass A): you score ALL dimensions and produce the
full per-dimension schema (coverage, fixes, etc.). Your output is the canonical scoring
pass; the orchestrator will run a Pass B against you (anchors only, after context
rotation) to compute test-retest reliability.
Single (anchor re-score) (--single-scorer, Pass B): you re-score ONLY the anchor
dimensions named in your prompt. You have just done a context rotation (read an unrelated
file) and re-read the framework from scratch. Produce a stripped schema per anchor:
dimension, score, band, evidence only — no coverage, no strengths/gaps, no fixes.
This pass is for reliability measurement, not for fix-loop content. Do not consult Pass A
output (you don't have it). Score as if you were a fresh evaluator looking at the rubric
for the first time — that's what the protocol is measuring.
When dispatched as a single agent without the --single-scorer flag (legacy inline mode),
score all dimensions and produce the full evaluation output but mark
scoring_confidence as "medium (+/-8 pts)" minimum to reflect the absence of any
calibration signal.
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.
- 2d ago First seen · 402 lines · 0 tokens per session scan A 70ad42c57572
evaluate-score is an agent published in the GitHub repository CoriChui/bakeoff (10 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,151 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.
Other agents, from other repositories
council-meadows
Council member. Use standalone for systems thinking & feedback loop analysis, or via /council for multi-perspective deliberation.
council-musashi
Council member. Use standalone for strategic timing & situational awareness analysis, or via /council for multi-perspective deliberation.
FLEET
Thirteen agents. Each has a charter, inputs, outputs, refusals and a handoff contract.
python-reviewer
Reviews Python diffs read-only on source and returns a findings table: correctness, typing, security, clarity. Writes only its report, to a caller-named path outside the repo. Spawn one per diff. Not for implementing (python-pro).
docs-reconciler
Reconciles README, docs/, CLAUDE.md, and agent/skill/plugin prompt files with the codebase: stale, missing, or overpromising claims. Edits docs only. Spawn one per repo.
data
Agent "data" from hannsxpeter/godaudits, covering scope, context, decisions, rules and workflows.