eval-report

eval-report is a skill for Claude Code from hoangsonww/AI-News-Briefing. It costs 49 tokens per session (444 once invoked), scanned A, original, MIT.

A tool for producing a weekly Markdown report of AI-news briefing quality scores. Markdown is plain text with simple formatting, and the report covers coverage, combined scores, category medians, and daily results.

In plain words
What is it for?
Use it for weekly quality summaries, drift investigations, or checking results after changing an evaluation method. It can print the report or save it to a file.
Why use it?
It turns stored evaluation results into a consistent digest for review or publication. It also avoids counting repeated evaluations of the same day more than once.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 eval/report.py --as-of YYYY-MM-DD --window 7 --out logs/eval-week.md.

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

Good fit Use it for weekly quality summaries, drift investigations, or checking results after changing an evaluation method. It can print the report or save it to a file.

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-report

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-report

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/hoangsonww/ai-news-briefing/eval-report"><img src="https://agentmods.dev/badge/skills/hoangsonww/ai-news-briefing/eval-report.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 444 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 $0.00049 $0.00444
Opus 5 $0.00024 $0.00222
Sonnet 5 $0.00010 $0.00089
Haiku 4.5 $0.00005 $0.00044

Measured 11d ago against content hash 535cfc9aef6a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

eval-report 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-report/SKILL.md · 42 lines

What it actually says

Eval — Weekly Markdown Report

Pull the trailing N-day window from eval/store.sqlite and emit a Markdown digest suitable for publishing to Notion / Teams / Slack, or for committing under logs/eval-reports/.

How to invoke

make eval-report D=YYYY-MM-DD W=7                            # 7-day window to stdout
make eval-report D=YYYY-MM-DD W=14 OUT=logs/eval-week.md     # write to file

Direct invocation:

python3 eval/report.py --as-of YYYY-MM-DD --window 7 --out logs/eval-week.md

Behavior

  1. Fetch all eval_runs rows in [as_of - window + 1, as_of].
  2. Pick the latest run per card_date (so re-runs don't double-count).
  3. Compute coverage (N / window days judged), composite min/max/median, and per-axis medians.
  4. Emit:
    • H1 header with the date range
    • Coverage + composite stats
    • Axis medians table
    • Per-day detail table (date, composite, F/N/D/S/C, judge model, truncated notes)

When to use

  • Monday morning summary across the previous 7 days.
  • Investigating a drift alert (make eval-drift) — the per-day table shows which axes are dragging.
  • After a re-baselining workflow, to confirm the new judge/prompt produces consistent quality.

What to tell the user

If OUT is set, mention the file path and a quick cat or preview command. If piping to stdout, show the digest verbatim (the user can scroll the terminal). For Notion/Teams publishing, point at scripts/notify-teams.sh or the Notion MCP — the harness intentionally does not publish on its own.

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 · 42 lines · 49 tokens per session scan A 535cfc9aef6a

Subscribe to this mod's changes

eval-report is a skill published in the GitHub repository hoangsonww/AI-News-Briefing (41 stars, last pushed 3d ago), licensed MIT. It adds 49 tokens to every session and 444 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.