evals

evals is a skill for Claude Code, Codex from muggl3mind/career-manager. It costs 43 tokens per session (367 once invoked), scanned A, original, MIT.

A checking system for a job-search software pipeline: a set of scripts that reviews its code, checks its results after a run, and monitors its ongoing health.

In plain words
What is it for?
Use it after changing pipeline code, after a pipeline run, or regularly to monitor the pipeline. It covers the career-manager/job-search scripts, data, and caches.
Why use it?
It helps catch coding problems, incorrect pipeline results, and declining reliability before they cause bigger issues.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it after changing pipeline code, after a pipeline run, or regularly to monitor the pipeline. It covers the career-manager/job-search scripts, data, and caches.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/muggl3mind/career-manager/evals
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 muggl3mind/career-manager --skill evals
Clone the repo
git clone --depth 1 https://github.com/muggl3mind/career-manager

Made for: Claude Code, Codex.

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 evals

README.md
[![agentmods](https://agentmods.dev/badge/skills/muggl3mind/career-manager/evals.svg)](https://agentmods.dev/skills/muggl3mind/career-manager/evals)
Your own site
<a href="https://agentmods.dev/skills/muggl3mind/career-manager/evals"><img src="https://agentmods.dev/badge/skills/muggl3mind/career-manager/evals.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 367 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.
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 $0.00043 $0.00367
Opus 5 $0.00022 $0.00183
Sonnet 5 $0.00009 $0.00073
Haiku 4.5 $0.00004 $0.00037

Measured 7d ago against content hash 9caed4946f35, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

evals 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 7d ago.

The scan reads SKILL.md. This mod also ships 22 executable files (scripts/code_review.py, scripts/health_monitor.py, scripts/runtime_verify.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

evals/SKILL.md · 48 lines

What it actually says

Evals

Independent evaluation suite for the job-search pipeline. Lives outside the pipeline it evaluates.

Evaluation Levels

Level Script When to Run
1. Code Review scripts/code_review.py After building or changing pipeline code
2. Runtime Verify scripts/runtime_verify.py After a pipeline run completes
3. Health Monitor scripts/health_monitor.py Recurring — every pipeline run or 2-3x/week

Process

  1. Run the relevant eval script for your situation
  2. Review the report output
  3. Fix issues (or flag for user approval if touching shared data)
  4. Re-run the eval to verify fixes

Usage

# Level 1: Static code review of job-search pipeline
python3 scripts/code_review.py

# Level 2: Validate outputs after a pipeline run
python3 scripts/runtime_verify.py

# Level 3: Ongoing health monitoring
python3 scripts/health_monitor.py
python3 scripts/health_monitor.py --json

Scope

  • Evaluates: career-manager/job-search/ (scripts, data, caches)
  • Does NOT evaluate: itself, other career-manager skills, or non-pipeline code
  • References: workflow-standards/references/evaluation.md for methodology

Output Format

Each script prints a check-by-check report with pass/warn/fail status and returns non-zero exit code if critical checks fail.

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. 7d ago First seen · 48 lines · 43 tokens per session scan A 9caed4946f35

Subscribe to this mod's changes

evals is a skill published in the GitHub repository muggl3mind/career-manager (24 stars, last pushed 4mo ago), licensed MIT. It adds 43 tokens to every session and 367 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.

Related

Other skills, from other repositories