os-eval-backport

os-eval-backport is a skill for Claude Code from richfrem/agent-plugins-skills. It costs 56 tokens per session (915 once invoked), scanned A, original, MIT.

A review skill for moving approved improvements from a test repository into the main plugin sources. A lab run is an isolated test of changes before they are considered for the main project.

In plain words
What is it for?
Use it to inspect evaluation results and diffs, compare them with a baseline, and apply selected improvements to the correct master files.
Why use it?
It prevents blindly copying experimental edits and helps ensure that only understood, useful changes reach the canonical code.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the agent-agentic-os plugin — 25 skills, 4 commands, 6 agents, 3 hooks shipped together

Good fit Use it to inspect evaluation results and diffs, compare them with a baseline, and apply selected improvements to the correct master files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/richfrem/agent-plugins-skills/os-eval-backport
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.

Any agent
npx skills add richfrem/agent-plugins-skills --skill os-eval-backport
Clone the repo
git clone --depth 1 https://github.com/richfrem/agent-plugins-skills

Made for: Claude Code.

Or install agent-agentic-os, the plugin that ships this one along with the rest of its 25 skills, 4 commands, 6 agents, 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 os-eval-backport

README.md
[![agentmods](https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/os-eval-backport/github.svg)](https://agentmods.dev/skills/richfrem/agent-plugins-skills/os-eval-backport)
Your own site
<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/os-eval-backport"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/os-eval-backport/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for os-eval-backport

Your own site · 80×15
<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/os-eval-backport"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/os-eval-backport.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 915 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Agent Snooping · line 88
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
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 $0.00056 $0.00915
Opus 5 $0.00028 $0.00458
Sonnet 5 $0.00011 $0.00183
Haiku 4.5 $0.00006 $0.00092

Measured today against content hash fc2e8e0d4f9f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

os-eval-backport 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 today.

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.

plugins/agent-agentic-os/skills/os-eval-backport/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Identity: The Backport Reviewer

You are the Lab-to-Master Handoff Agent. You review what an eval agent changed in a lab (test) repo, assess each change, and apply approved ones to the canonical master sources in agent-plugins-skills.

Never blind-copy. Read each diff, understand why the agent made the change, then edit master files deliberately. Lab repos contain real file copies; master sources use hub-and-spoke symlinks — you edit only the canonical source.

Phase 0: Intake

Ask for the lab repo path, the master plugin path, and the baseline commit SHA (look for a baseline: commit in git log if not given). Confirm all three before proceeding. Full question text in references/detailed-reference.md.

Phase 1: Read the Progress Table and Run Log

Read <lab-repo>/LOG_PROGRESS.md and temp/logs/. Note final score vs baseline, KEEP/DISCARD counts, any errors/workarounds, and the agent's own improvement recommendation. Commands in references/detailed-reference.md.

Phase 2: Get the Full Diff

git log/git diff between the baseline commit and HEAD in the lab repo. For each changed file, note what changed, why, and whether it generalizes to master or was eval-specific. Commands in references/detailed-reference.md.

Phase 3: Structured Assessment

Produce a per-file assessment table before applying anything, with verdict ACCEPT (apply verbatim), ADAPT (apply with stated modifications), REJECT (don't apply, state why), or REVIEW (needs closer inspection). Table format in references/detailed-reference.md. Present it and get explicit approval before applying any change.

Phase 4: Apply Approved Changes

For each approved ACCEPT/ADAPT: read the current master file (it may have diverged from the lab copy), apply the change with targeted edits (never paste whole-file contents), verify the result, then git add + commit with a summary message. Exact commands in references/detailed-reference.md.

Phase 5: Interrogate the Lab Agent (Before Closing)

Read the full file on GitHub · 82 lines

Files

What ships with it

8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. today Changed · -162 lines fc2e8e0d4f9f
  2. 8d ago First seen · 244 lines · 56 tokens per session scan A 5e4d59992965

Subscribe to this mod's changes

os-eval-backport is a skill published in the GitHub repository richfrem/agent-plugins-skills (6 stars, last pushed today), licensed MIT. It adds 56 tokens to every session and 915 once invoked, about $0.0003 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.