claude-ruby-grape-rails eval-review.instructions.md

Review rules for an evaluation framework, where test definitions and example prompts measure how well an AI skill behaves.

In plain words
What is it for?
Use them when reviewing evaluation definitions, trigger-prompt collections, scoring checks, and context-size limits in a Ruby Grape Rails project.
Why use it?
They keep evaluation files consistent, reduce accidental test bias, and limit the amount of guidance loaded into the agent's context.

Instructions file for GitHub Copilot

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 instructions/slbug/claude-ruby-grape-rails/eval-review
Clone the repo
git clone --depth 1 https://github.com/slbug/claude-ruby-grape-rails

Made for: GitHub Copilot.

Per session 1,586 This file is loaded in full into every session.
When invoked 1,586 The same file — it is already loaded in full.
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 $0.01586 $0.01586
Opus 5 $0.00793 $0.00793
Sonnet 5 $0.00317 $0.00317
Haiku 4.5 $0.00159 $0.00159

Measured 2d ago against content hash 082851a01a47, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude-ruby-grape-rails eval-review.instructions.md 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.

.github/instructions/eval-review.instructions.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Eval Framework Review Rules

Audience: Agents, Not Humans

Imperative-only.

Eval Definitions (lab/eval/evals/*.json)

  • Each JSON defines dimensions: completeness, accuracy, conciseness, triggering, safety, clarity
  • Each dimension has a weight (float, all weights should sum to ~1.0) and an array of checks
  • Check types must match functions in matchers.py MATCHERS dict
  • Skill-specific checks override the default_eval() fallback in scorer.py
  • Eval definitions should not exceed 3KB

Trigger Corpora (lab/eval/triggers/*.json)

  • Each JSON has: skill, should_trigger, should_not_trigger, hard_should_trigger, hard_should_not_trigger
  • Minimum counts: 4 should_trigger, 4 should_not_trigger, 2 hard_should_trigger, 2 hard_should_not_trigger
  • Hard prompts must have an axis field with >= 2 distinct values across hard_should_trigger (typically "confusable" and "multi_step")
  • Prompts must not contain skill names (routing contamination)
  • No duplicate prompts within a file (normalized comparison)

Context Budget (lab/eval/context_budget.py)

  • Advisory checks for CLAUDE.md size and aggregate routing-prompt char budget (8,000-char hard ceiling on the skill listing per CC routing budget)
  • Zero API cost — file reads and frontmatter scanning only
  • Wired into --changed, --all, and --ci modes in run_eval.sh

Module Map

The canonical module list is ls lab/eval/*.py. Re-derive on every review pass; do not rely on a frozen enumeration here.

When reviewing a change under lab/eval/:

  1. Read the module's docstring and import block — they declare its role and whether it touches an LLM provider.
  2. Check whether make eval-ci-deterministic reaches it transitively (see lab/eval/run_eval.sh --ci body and the allowlist in lab/eval/tests/test_eval_ci_determinism.py::DETERMINISTIC_PATH_FILES). Modules on that path MUST stay LLM-free.
  3. LLM-bearing modules (behavioral_scorer.py, epistemic_suite.py, trigger_scorer.py --semantic path) are intentionally OFF the deterministic path. Confirm any new transport import goes into one of those, not into the deterministic path.

Read the full file on GitHub · 139 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 · 139 lines · 1,586 tokens per session scan A 082851a01a47

Subscribe to this mod's changes

claude-ruby-grape-rails eval-review.instructions.md is an instructions file published in the GitHub repository slbug/claude-ruby-grape-rails (7 stars, last pushed 3d ago), licensed MIT. It adds 1,586 tokens to every session, about $0.0079 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.