What is update-refine?

A job-independent wording pass that improves a resume using best-practice checks. It applies safe suggestions automatically and asks the user for facts when a rewrite needs real information.

Use it after the resume has been put into standard sections and checked for best practices, before tailoring it to a specific job.

It improves clarity and consistency without inventing achievements, skills, or other claims.

update-refine — Skill for Claude Code and Codex by dcassil: A job-independent wording pass that improves a resume using…

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 skills/dcassil/resume-kit/update-refine

Any agent

npx skills add dcassil/resume-kit --skill update-refine

Clone the repo

git clone --depth 1 https://github.com/dcassil/resume-kit

Made for: Claude Code, Codex.

Or install resume-intelligence, the plugin that ships this one along with the rest of its 31 skills, 1 command, 1 hook.

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/skills/dcassil/resume-kit/update-refine.svg)](https://agentmods.dev/skills/dcassil/resume-kit/update-refine)

Your own site

<a href="https://agentmods.dev/skills/dcassil/resume-kit/update-refine"><img src="https://agentmods.dev/badge/skills/dcassil/resume-kit/update-refine.svg" alt="Measured on agentmods" height="20"></a>

Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,124 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	$0.00093	$0.01124
Opus 5	$0.00046	$0.00562
Sonnet 5	$0.00019	$0.00225
Haiku 4.5	$0.00009	$0.00112

Measured 4d ago against content hash 09c5b0183572, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

update-refine 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 4d 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/resume-intelligence/skills/update-refine/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

update-refine — structure/base → refine (best-practices wording pass)

Formerly update-best-practices (the standard pass); renamed in RIT-I-0020.

Baselining step 3 of original → base → structure → refine (RIT-I-0016). Turns the best-practices findings from check-best-practices into the refine version: auto_suggestible rewrites are applied deterministically, and needs_user_input items are resolved by asking the user for the real fact — never by inventing one. Drives the build-refine capability, which writes <name>-refine.json behind the claim-preservation gate and sets the refine pointer that all downstream tailoring then prefers.

Prerequisites

Run the shared Prerequisites gate — ../_shared/prerequisites.md.

Required inputs: a structure ResumeDocument JSON (run update-shape first; falls back to base only with a recorded shape-pass override), and the best-practices report from check-best-practices.
Does NOT need a job. The refine pass is job-independent.
If no structure exists: run update-shape first, or record the explicit override before using base.

The walkthrough

Score. Run check-best-practices on structure (or the overridden base) to get the findings, split into auto_suggestible and needs_user_input.
Elicit facts for needs_user_input items. For each such finding, show its elicitation_prompt and ask the user for the real fact (e.g. an actual metric). Collect answers into an answers map keyed by the finding key (resume_kit_scoring.finding_key). If the user cannot supply a fact, leave that finding unanswered — it will be reported as deferred, never fabricated.
Build refine. Call build-refine with the answers map. It applies the auto_suggestible rewrites plus the user-supplied answers, enforces the claim-preservation gate (the wording pass may reword but must not add, drop, or alter an employer/title/degree/skill claim), writes resume-kit/resumes/<name>-refine.json, and records the refine pointer.
Report. Show applied (edits made) and deferred (needs_user_input findings left unanswered). Optionally record a user's declined suggestion via learn-change so future runs weight it.

Read the full file on GitHub · 91 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.

4d ago First seen · 91 lines · 93 tokens per session scan A 09c5b0183572

Subscribe to this mod's changes

update-refine is a skill published in the GitHub repository dcassil/resume-kit (0 stars, last pushed 24d ago), licensed Apache-2.0. It adds 93 tokens to every session and 1,124 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.

Writing and docs

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens