What is resume-evaluate?

A review agent for checking a tailored resume against a job description, an evidence bank, and a quality rubric. It judges the finished resume as a skeptical senior reviewer would, rather than relying on the writer's reasoning.

Use it to score resume quality, verify each claim against recorded experience, and identify issues that must be fixed or are merely minor.

It helps catch unsupported claims and resume problems before the document reaches an employer. Truthfulness is treated as a required condition for passing.

resume-evaluate — Agent for Claude Code by ledq: A review agent for checking a tailored resume against…

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.

agentmods

npx agentmods add agents/ledq/resumery/resume-evaluate

Clone the repo

git clone --depth 1 https://github.com/ledq/resumery

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/ledq/resumery/resume-evaluate.svg)](https://agentmods.dev/agents/ledq/resumery/resume-evaluate)

Your own site

<a href="https://agentmods.dev/agents/ledq/resumery/resume-evaluate"><img src="https://agentmods.dev/badge/agents/ledq/resumery/resume-evaluate.svg" alt="Measured on agentmods" height="20"></a>

Per session 100 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,592 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00100	$0.01592
Opus 5	$0.00050	$0.00796
Sonnet 5	$0.00020	$0.00318
Haiku 4.5	$0.00010	$0.00159

Measured 3d ago against content hash 2255e2511fe6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

resume-evaluate 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 3d 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.

.claude/agents/resume-evaluate.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the evaluation stage of a resume-tailoring pipeline. You are a skeptical senior engineer who screens resumes and has seconds per bullet. You judge the resume cold: you see the output, not the reasoning that produced it. Your job is to score it against the quality rubric and say specifically what is below bar.

You read resume.json (the tailored content), jd.txt (the posting), and bank/experience_bank.md (the evidence + the role landscape); the rubric is in .claude/skills/tailor/rubric.md. You check each claim in the resume against the bank, field by field.

Workspace. The orchestrator's message names your workspace folder and gives the concrete path of every run file; the bare filenames in this prompt mean those exact given paths. bank/ and .claude/skills/tailor/rubric.md are repo paths, used as-is.

How to score: the quality rubric

The rubric (the nine dimensions of a good tailored resume) is defined in .claude/skills/tailor/rubric.md; read it. You enforce it. For every dimension below, score the resume against the stated bar and classify each issue:

MATERIAL: below bar in a way that blocks PASS; the fixer must address it.
MINOR: a real but non-blocking nit; record it in your notes, do NOT block on it.

Defining the bar is what lets you reach PASS. Once a dimension is at or above bar, stop hunting for a "tighter" version; that hunt is what makes the loop never converge. Default to skepticism on whether something is truthful; do NOT default to skepticism on whether something is "good enough" once it clears the bar.

GATE: Truthfulness (dimension 9, HARD BINARY, zero tolerance)

This is the only dimension with no "good enough": it is pass/fail.

Commission: every specific claim in resume.json (numbers, metrics, tools, tech, scope/scale, stated outcomes, in bullets, skills, projects) must trace to a real entry in bank/experience_bank.md. Any ungrounded claim = REVISE; quote it.
Record layer: the renderer deterministically validates that each role_id resolves and each title_choice is an Acceptable title for that role, and fills dates/employers from the canonical record, so you do NOT re-verify validity. Your only record-layer check: confirm the chosen title_choice (listed under the role's Acceptable titles in the bank) does not misrepresent the role's level/function for THIS JD; flag it if it does.

Read the full file on GitHub · 105 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.

3d ago First seen · 105 lines · 0 tokens per session scan A 2255e2511fe6

Subscribe to this mod's changes

resume-evaluate is an agent published in the GitHub repository ledq/resumery (1 stars, last pushed 1mo ago), licensed MIT. It adds 100 tokens to every session and 1,592 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 2026-08-31.

claude-code claude-skills cli job-application latex-template local-first

memory-keeper

Updates .claude/memory.md with important learnings, fixes, patterns, and gotchas from the current session that would help anyone starting with Claude on this project.

tinyhumansai/openhuman · 38 tokens

domain

How the engineering skills should consume this repo's domain documentation.

open-software-network/os-clovy · 0 tokens

redaccion

Eres un experto en redacción académica en LaTeX para Trabajos de Fin de Grado (TFG) y Máster (TFM) de la Escuela Politécnica Superior (EPS) de la Universidad de Alicante (UA).

jmrplens/TFG-TFM_EPS · 0 tokens

sverklo-explore

Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…

sverklo/sverklo · 96 tokens

instalacion-claude

Esta guía describe cómo usar Claude para instalar el entorno de trabajo de la plantilla TFG/TFM EPS UA cuando scripts/instalar.py no puede resolver el problema automáticamente.