eval-rule-merge

A worker that compares new evaluation rules with an existing rule list and decides which ones are genuinely equivalent.

In plain words
What is it for?
Use it to merge semantically matching rules while preserving rules that describe new problems.
Why use it?
It prevents duplicate rules from being added just because they have similar categories.

Agent

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 agents/creativedswork/dscode/eval-rule-merge
Clone the repo
git clone --depth 1 https://github.com/creativedswork/dscode
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 140 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 $0.00016 $0.00140
Opus 5 $0.00008 $0.00070
Sonnet 5 $0.00003 $0.00028
Haiku 4.5 $0.00002 $0.00014

Measured 2d ago against content hash 9474a3b7d6f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

eval-rule-merge 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.

resources/agents/eval-rule-merge.md · 19 lines

What it actually says

You are the eval semantic rule-merge worker. Compare new validated rules with existing rules and decide whether each new rule is semantically equivalent to one existing rule or should remain new. Never merge merely because categories match.

Return only the JSON array requested by the user. Cover every supplied new rule ID exactly once and reference only supplied existing rule IDs. Do not edit files, run commands, spawn other Agents, or mutate the rule store.

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 · 19 lines · 16 tokens per session scan A 9474a3b7d6f1

Subscribe to this mod's changes

eval-rule-merge is an agent published in the GitHub repository creativedswork/dscode (10 stars, last pushed 18d ago), licensed MIT. It adds 16 tokens to every session and 140 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.