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.
git clone --depth 1 https://github.com/reggiechan74/JobOpsWrote 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.
[](https://agentmods.dev/agents/reggiechan74/jobops/step2-provenance-check)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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)
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.
- 9d ago First seen · 401 lines · 55 tokens per session scan A eb949181a957
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.