step2-provenance-check

step2-provenance-check is an agent for Claude Code from reggiechan74/JobOps. It costs 55 tokens per session (4,640 once invoked), scanned A, original, MIT.

A resume-review agent that checks a draft against source materials and a job description for credibility risks and missing evidence.

In plain words
What is it for?
Use it to produce a provenance report with specific recommendations before finalizing a resume.
Why use it?
It identifies claims that may be hard to defend, such as unexplained numbers, vague results, or unsupported praise.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the jobops plugin — 26 skills, 17 agents shipped together

Good fit Use it to produce a provenance report with specific recommendations before finalizing a resume.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/reggiechan74/jobops/step2-provenance-check
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.

Clone the repo
git clone --depth 1 https://github.com/reggiechan74/JobOps

Made for: Claude Code.

Or install jobops, the plugin that ships this one along with the rest of its 26 skills, 17 agents.

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 step2-provenance-check

README.md
[![agentmods](https://agentmods.dev/badge/agents/reggiechan74/jobops/step2-provenance-check/github.svg)](https://agentmods.dev/agents/reggiechan74/jobops/step2-provenance-check)
Your own site
<a href="https://agentmods.dev/agents/reggiechan74/jobops/step2-provenance-check"><img src="https://agentmods.dev/badge/agents/reggiechan74/jobops/step2-provenance-check/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 step2-provenance-check

Your own site · 80×15
<a href="https://agentmods.dev/agents/reggiechan74/jobops/step2-provenance-check"><img src="https://agentmods.dev/badge/agents/reggiechan74/jobops/step2-provenance-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,640 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 $0.00055 $0.04640
Opus 5 $0.00028 $0.02320
Sonnet 5 $0.00011 $0.00928
Haiku 4.5 $0.00006 $0.00464

Measured 9d ago against content hash eb949181a957, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

step2-provenance-check 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 9d 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.

plugins/jobops/agents/step2-provenance-check.md · 401 lines

How it starts

The opening of the file, as written. The whole thing — 401 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a provenance analysis specialist focused on credibility verification and risk assessment. Your role is Step 2 of a three-step resume creation process.

Your Mission

Conduct comprehensive provenance analysis on Step 1 resume drafts to identify credibility issues, evidence gaps, and provide specific recommendations for creating a defensible final resume.

Input Requirements

You expect to analyze:

  • Step 1 Draft Resume: at the path provided by the dispatching skill (convention: {app_slug}/resume/step1_draft.md)
  • Master Resume Materials: Available in /ResumeSourceFolder/
  • Job Description: The target role requirements
  • Evidence Sources: Any additional supporting documentation

Provenance Analysis Methodology

You will apply the CV Provenance Hardening methodology with these detection heuristics:

Risk Detection Heuristics

A. Unbounded Metrics: Numbers with no time-box (e.g., "increased by 50%" without dates) B. Mechanism-Free Outcomes: Results with no "how" (e.g., "cut cycle time" with no tool/process) C. Evidence-Free Superlatives: "market-leading," "innovative," "transformational," "world-class," "best-in-class," "proven track record," "expert in," "successfully," "demonstrated ability," "responsible for" (without outcomes) D. Cross-Doc Inconsistencies: Numbers, dates, titles, or scopes that conflict with master resume E. Duplicate Wins: Same achievement repeated across roles without consolidation F. Unsupported Publications/Awards: Citation missing volume/date/issuer G. Ambiguous Scope: Claim lacks portfolio size, geography, asset type, or role boundaries H. Confidentiality Risk: Proprietary figures/names not necessary for verification I. Benchmark Claims Without Benchmarks: "top quartile," "market-leading" without defined peer set J. Tool Name Without Effect: Systems listed without measurable outcome K. Fabricated Claims: Any capability, experience, skill, or achievement not explicitly documented in master materials (e.g., language skills, industry experience, technical capabilities with no supporting evidence)

Read the full file on GitHub · 401 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. 9d ago First seen · 401 lines · 55 tokens per session scan A eb949181a957

Subscribe to this mod's changes

step2-provenance-check is an agent published in the GitHub repository reggiechan74/JobOps (25 stars, last pushed 3mo ago), licensed MIT. It adds 55 tokens to every session and 4,640 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 2026-08-30.