eval-backfill

eval-backfill is a skill for Claude Code from hoangsonww/AI-News-Briefing. It costs 46 tokens per session (375 once invoked), scanned A, original, MIT.

An evaluation job that scores every card in the project’s example-cards folder and saves the results in a local SQLite database. An evaluation harness is a tool for running the same quality checks across many examples.

In plain words
What is it for?
Use it when you need to backfill scores, score all cards, or run a quality check across the complete example set.
Why use it?
It removes the need to score each example manually and keeps the results for later review.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: positional $N argument.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 eval/runner.py backfill --judge claude --workers 4 --max-calls 50.

Part of the ai-news-briefing plugin — 11 skills, 3 agents, 1 hook, 2 MCP servers shipped together

Good fit Use it when you need to backfill scores, score all cards, or run a quality check across the complete example set.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/hoangsonww/AI-News-Briefing
agentmods
npx agentmods add skills/hoangsonww/ai-news-briefing/eval-backfill

Made for: Claude Code.

Or install ai-news-briefing, the plugin that ships this one along with the rest of its 11 skills, 3 agents, 1 hook, 2 MCP servers.

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-backfill

README.md
[![agentmods](https://agentmods.dev/badge/skills/hoangsonww/ai-news-briefing/eval-backfill/github.svg)](https://agentmods.dev/skills/hoangsonww/ai-news-briefing/eval-backfill)
Your own site
<a href="https://agentmods.dev/skills/hoangsonww/ai-news-briefing/eval-backfill"><img src="https://agentmods.dev/badge/skills/hoangsonww/ai-news-briefing/eval-backfill/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 eval-backfill

Your own site · 80×15
<a href="https://agentmods.dev/skills/hoangsonww/ai-news-briefing/eval-backfill"><img src="https://agentmods.dev/badge/skills/hoangsonww/ai-news-briefing/eval-backfill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 375 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 pass 7 Sept 2026
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 $0.00046 $0.00375
Opus 5 $0.00023 $0.00187
Sonnet 5 $0.00009 $0.00075
Haiku 4.5 $0.00005 $0.00038

Measured 11d ago against content hash f05faf27c5dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

eval-backfill 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 11d 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.

claude-plugins/ai-news-briefing/skills/eval-backfill/SKILL.md · 33 lines

What it actually says

Eval — Backfill All Cards

Score every card in example-cards/*-card.json and write rows to eval/store.sqlite.

How to invoke

make eval-backfill                       # stub judge, offline
make eval-backfill JUDGE=claude          # real Claude Haiku judge, ~$0.04 for 18 cards

Direct invocation supports --workers and --max-calls:

python3 eval/runner.py backfill --judge claude --workers 4 --max-calls 50

Behavior

  • Stub runs serially (instant).
  • Real backends parallelize via a ThreadPoolExecutor (default 4 workers). 18 cards usually finish in ~3-5 minutes.
  • A pre-call status line prints per card ([HH:MM:SS] YYYY-MM-DD: judging...). Full subprocess traces append to logs/eval-judge-YYYY-MM-DD.log so the user can tail -f while it runs.
  • Failures on individual cards are logged but do not abort the whole backfill.
  • --max-calls 50 caps accidental sweeps; bump it deliberately if the cap is hit.

What to tell the user

Show the trailing summary: number of cards judged, total elapsed time, per-card amortized cost. If any card failed, surface the failing date and the error. Mention tail -f logs/eval-judge-$(date +%F).log so the user can monitor progress without re-running.

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. 11d ago First seen · 33 lines · 46 tokens per session scan A f05faf27c5dd

Subscribe to this mod's changes

eval-backfill is a skill published in the GitHub repository hoangsonww/AI-News-Briefing (41 stars, last pushed 3d ago), licensed MIT. It adds 46 tokens to every session and 375 once invoked, about $0.0002 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 2026-08-30.