eval-merge

eval-merge is a command for coding agents from Evol-ai/SkillCompass. It costs 0 tokens per session (924 once invoked), scanned A, original, MIT.

A command for combining your edited version of a skill with newer changes from its original source. A three-way merge compares the shared starting version, your version, and the updated source.

In plain words
What is it for?
Use it when a tracked skill has a known original source and that source has changed. It is intended for updating local skill instructions while preserving local improvements.
Why use it?
It helps bring in upstream updates without losing changes you made locally. It also checks that version history exists and that an actual update is available before merging.

Command

Part of the SkillCompass plugin — 1 skill, 14 commands, 3 hooks shipped together

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/evol-ai/skillcompass/eval-merge
Clone the repo
git clone --depth 1 https://github.com/Evol-ai/SkillCompass

Or install SkillCompass, the plugin that ships this one along with the rest of its 1 skill, 14 commands, 3 hooks.

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 eval-merge

README.md
[![agentmods](https://agentmods.dev/badge/commands/evol-ai/skillcompass/eval-merge.svg)](https://agentmods.dev/commands/evol-ai/skillcompass/eval-merge)
Your own site
<a href="https://agentmods.dev/commands/evol-ai/skillcompass/eval-merge"><img src="https://agentmods.dev/badge/commands/evol-ai/skillcompass/eval-merge.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 924 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 $0.00000 $0.00924
Opus 5 $0.00000 $0.00462
Sonnet 5 $0.00000 $0.00185
Haiku 4.5 $0.00000 $0.00092

Measured 4d ago against content hash 803e842f636f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

eval-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 4d 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/eval-merge.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/eval-merge — Three-Way Version Merge

Locale: All templates in this spec are written in English. Detect the user's language from the session and translate user-facing text at display time per SKILL.md's Global UX Rules. Dimension labels: see the canonical table in SKILL.md.

Arguments

  • <path> (required): Path to the SKILL.md file (local evo version).
  • --upstream <path-or-url> (optional): Path to upstream version. If omitted, detect from manifest.
  • --internal (optional): Skip interactive prompts; use defaults for automated pipelines.
  • --ci (optional): Alias for --internal.

Pre-conditions

Use the Read tool to load .skill-compass/{skill-name}/manifest.json. Verify:

  1. upstream_origin exists in manifest (skill has a known upstream source)
  2. At least 1 evo version exists (something to preserve)
  3. Upstream version differs from last known upstream (there IS an update)

If any pre-condition fails: display the failure reason in the session locale and stop. Do not show raw error codes or internal field names — describe the problem and, where possible, suggest what the user can do next.

Steps

Step 1: Identify Three Versions

  • Base: the last known upstream version from manifest (upstream_origin.last_known_version). Load from snapshots.
  • Local: the current evo version (the file at <path>).
  • Upstream: the new upstream version (from --upstream flag or auto-detected).

Use the Read tool to load all three versions.

Step 2: Execute Merge

Use the Read tool to load {baseDir}/prompts/merge.md. Pass:

  • {BASE_VERSION}: base content
  • {LOCAL_VERSION}: local content
  • {UPSTREAM_VERSION}: upstream content

Follow the merge prompt's region-by-region strategy. Present conflicts to the user for resolution.

Step 3: Write Merged Version

After all conflicts resolved, display the complete merged SKILL.md. Ask user for confirmation before writing.

If confirmed: use the Write tool to save the merged version.

Read the full file on GitHub · 92 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. 4d ago First seen · 92 lines · 0 tokens per session scan A 803e842f636f

Subscribe to this mod's changes

eval-merge is a command published in the GitHub repository Evol-ai/SkillCompass (215 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 924 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 2026-08-30.