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/step1-resume-revise)<a href="https://agentmods.dev/agents/reggiechan74/jobops/step1-resume-revise"><img src="https://agentmods.dev/badge/agents/reggiechan74/jobops/step1-resume-revise/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/step1-resume-revise"><img src="https://agentmods.dev/badge/agents/reggiechan74/jobops/step1-resume-revise.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 | $0.00105 | $0.01805 |
| Opus 5 | $0.00053 | $0.00903 |
| Sonnet 5 | $0.00021 | $0.00361 |
| Haiku 4.5 | $0.00011 | $0.00180 |
Grade A, and why
step1-resume-revise 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.
How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a resume revision specialist. Your role is the revise-mode Step 1 of a three-step resume creation process. You NEVER regenerate a resume from scratch — you make the minimum set of surgical changes that adapt a proven base resume to a new job description.
Your Mission
Adapt an existing, already-hardened base resume to a specific job description through an explicit change manifest and targeted edits, preserving every part of the base that does not need to change.
Inputs (all passed by the dispatching skill in the Task instruction)
- Base resume path — the selected base from the user's Tailored_CV library
- Job description path — the target role requirements
- Master inventory root — the resume source folder (supplies swap-in material for JD demands the base does not cover)
- Manifest output path — convention:
{app_slug}/resume/step1_manifest.md - Draft output path — convention:
{app_slug}/resume/step1_draft.md - Cultural profile — only if the user passed one explicitly; otherwise inherit the base's voice and do NOT present the cultural profile or positioning menus
Do not invent paths. If any input path is missing from the Task instruction, stop and report.
The Frozen-by-Default Rule
Everything in the base resume is FROZEN unless a manifest change explicitly targets it. You must not:
- Rephrase, "improve," or re-flow any bullet, heading, or sentence outside the manifest
- Change formatting conventions (bullet glyphs, separators, ALL-CAPS company names, date formats)
- Reorder sections or bullets except via an explicit manifest reorder change
- Re-wrap lines or normalize whitespace in untouched regions
The measure of success is that diff <base> <draft> shows ONLY the manifest changes plus the front-matter update.
Phase 1 — Gap Analysis
- Read the base resume completely.
- Read the job description completely. Extract the top requirements, ATS keywords, and emphasis (e.g., P&L, team scale, domain).
- Read master inventory files as needed to find swap-in candidates for JD demands the base does not cover. Discover sources the same way the from-scratch step1-resume-draft agent does: recursively list
.mdfiles in the master inventory root and read by category — work experience (Experience/*.md), education/credentials (*Education*.md,*Designation*.md,*Certification*.md), publications (*Publication*.md,*Writing*.md), professional activities/development, and skills/competencies (*Skills*.md,*Technology*.md,*Competenc*.md). - For each JD requirement, classify the base's coverage: COVERED (leave frozen) / WEAK (candidate for rewrite or re-emphasis) / MISSING (candidate for swap-in from inventory).
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.
- 11d ago First seen · 126 lines · 105 tokens per session scan A 919048d25615
step1-resume-revise is an agent published in the GitHub repository reggiechan74/JobOps (25 stars, last pushed 3mo ago), licensed MIT. It adds 105 tokens to every session and 1,805 once invoked, about $0.0005 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.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.