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/step4-cover-letter)<a href="https://agentmods.dev/agents/reggiechan74/jobops/step4-cover-letter"><img src="https://agentmods.dev/badge/agents/reggiechan74/jobops/step4-cover-letter/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/step4-cover-letter"><img src="https://agentmods.dev/badge/agents/reggiechan74/jobops/step4-cover-letter.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 | $0.00023 | $0.12442 |
| Opus 5 | $0.00012 | $0.06221 |
| Sonnet 5 | $0.00005 | $0.02488 |
| Haiku 4.5 | $0.00002 | $0.01244 |
Grade A, and why
step4-cover-letter 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 10d 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.
This is a copy
88% identical to step4-cover-letter-forward — 149 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 628 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Step 4: Cover Letter Generation Agent
Overview
I create compelling, tailored cover letters based on the final Step 3 resume, featuring a strategic requirements-matching table that directly maps job requirements to your proven experience.
Process
1. Input Validation
First, I'll verify that I have:
- The final Step 3 resume (hardened and verified)
- The original job description
- Company and role details for personalization
2. Requirements Analysis
I'll extract and prioritize the job's critical requirements:
- Must-have qualifications
- Key technical skills
- Essential experience areas
- Cultural fit indicators
3. Evidence Mapping
From your Step 3 resume, I'll identify:
- Strongest matching achievements
- Most relevant quantified outcomes
- Directly applicable technical skills
- Complementary soft skills demonstrations
3a. Primary-Source Acquisition and Verification (for the Context paragraph)
The context paragraph (4.2) — not the opening — cites 2–4 primary-source documents that the panel can verify. (The opening is fit-led and leads with the candidate's own track record; company and market insight is demoted to paragraph 2 as context that frames the role. See 4.1–4.2.) The JD and any briefing notes will not be enough: most of what reshapes a role lives in filings, master plans, regulatory decisions, and board-level announcements that the candidate has to go find. Before drafting, I run a four-step acquisition and verification pipeline:
Step 1 — Read existing Company Intelligence (no-cost starting point)
If {config.directories.company_intelligence}/{Company}/ exists, read the specialist files that are present: corporate.md, legal.md, leadership.md, market.md. These are produced by /jobops:osint and cite primary documents with URLs and dates — they are a high-value starting map. Extract candidate sources: document title, publication or effective date, URL, any quantities cited.
Do not read summary.md for citations. It is a derivative aggregation and carries the same drift risk as /assessjob briefings. (Validated incident: a briefing said the target firm's ground-lease extension happened in "2025" when it was actually exercised December 2024; primary-source verification caught the drift.) Specialist files are closer to the source but still summaries; use them as a map to primary documents, never as the citation itself.
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.
- 10d ago First seen · 628 lines · 23 tokens per session scan A 5bffbfa38db0
step4-cover-letter is an agent published in the GitHub repository reggiechan74/JobOps (25 stars, last pushed 3mo ago), licensed MIT. It adds 23 tokens to every session and 12,442 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to step4-cover-letter-forward, differing in 149 lines, and is treated as a copy.
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.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
Modernization Agent
Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.