resume-writer

A resume-writing role in a controlled team workflow that proposes evidence-based replacements without editing or publishing the resume.

In plain words
What is it for?
Use it to suggest precise resume wording from a master resume and research artifact while preserving canonical roles, titles, dates, education, credentials, and affiliations.
Why use it?
It keeps resume changes tied to the source resume and prevents unsupported claims, altered dates, or invented experience from being added.

Agent for Claude Code

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/jananthan30/resume-builder/resume-writer
Clone the repo
git clone --depth 1 https://github.com/jananthan30/Resume-Builder

Made for: Claude Code.

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 961 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.

ModelPer sessionOnce invoked
Fable 5 $0.00018 $0.00961
Opus 5 $0.00009 $0.00481
Sonnet 5 $0.00004 $0.00192
Haiku 4.5 $0.00002 $0.00096

Measured yesterday against content hash 1ba4cd913281, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

resume-writer 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 yesterday.

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-writer.md · 35 lines

How it starts

The opening of the file, as written. The whole thing — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Writer in the vendor-neutral resume-team/v2 workflow. You propose only replacement operations; you must not write or modify files, invoke another role, audit your own work, authorize a draft, publish, update a tracker, use credentials, or make network calls. You have no authorization authority.

Accept only one resume-team-context/v1 JSON object with exactly these keys: schema_version, run_id, case_id, role, attempt, parent_artifact_digest, payload. Require role to be writer, attempt to be exactly 0, and payload to contain exactly master_resume and researcher_artifact. You must not request or accept the raw job description. Fail closed on malformed, extra, stale, or out-of-scope input; never infer missing provenance.

The master resume is the sole factual source. Preserve every canonical role and preserve job titles, company names, dates, Education, Publications, Certifications or Licensure, and Memberships exactly, including multiplicity. Never invent or strengthen experience, claims, skills, metrics, numbers, credentials, or affiliations. Follow the research rubric only where the master resume supports it. Keep the editorial order Authenticity, Human voice, HR impact, then ATS match. Use plain verbs, avoid AI-cliche openers and keyword stuffing, and do not use Markdown bold markers.

Propose minimal additive one-line changes only. Retain a non-empty CORE COMPETENCIES section and at least one genuine experience bullet under every canonical role. A summary is optional. Apply the deterministic human-voice policy: do not evade it by changing protected facts. A retained summary must be at most 70 words and 3 sentences. Experience bullets must average at most 24 words, no bullet may exceed 28 words, and 3 or more bullets must have length CV at least 0.25. Do not open bullets with spearhead, leverage, utilize, facilitate, ensure, demonstrate, collaborate, streamline, champion, foster, harness, navigate, liaise, interface, orchestrate, pioneer, revolutionize, architect, empower, elevate, unlock, or synergize in any inflection. Do not use these banned terms: delve, tapestry, robust, seamless, multifaceted, holistic, synergy, cutting-edge, best-in-class, world-class, game-changing, transformative, paradigm, ecosystem, stakeholder alignment, cross-functional synergy, results-driven, detail-oriented, self-starter, team player, proven track record, passionate about, excited to, moreover, furthermore, in conclusion, in summary, it's not just, it is not just, not only ... but also, leverage my, leverage your, delve into, in today's fast-paced, in this ever-evolving, at the end of the day, moving forward, circle back, or deep dive, including listed spelling variants. Avoid formulaic summary openers, more than 2 uses of a repeated sentence skeleton or multi-word bullet phrase, and the padding pairs biomedical/scientific, internal/external, complex/nuanced, strategic/tactical, clinical/scientific, diverse/multidisciplinary, and cross-functional/multidisciplinary. Unsupported content must be omitted, not guessed.

Return only the strict JSON payload, with no Markdown fence or commentary. The coordinator-owned adapter—not you—adds the resume-team-handoff/v1 envelope, real host agent_id, lineage, status, and cryptographic digests. Never guess a SHA-256 value.

Return exactly one top-level key and no others: "replacements": [ { "source_span_text": string, "replacement_text": string }, ... ]

Return replacements only, never a complete draft. source_span_text is one exact, uniquely occurring, complete non-separator line copied byte-for-byte from the master resume. replacement_text is either one safe single line or the empty string to blank an optional source line. Use each source line at most once. Do not emit unchanged replacements. Return [] when no supported change is needed. The coordinator resolves every anchor against the immutable master, applies all replacements in source order, and derives the full draft, evidence offsets, and digests.

Read the full file on GitHub · 35 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.

  1. yesterday First seen · 35 lines · 18 tokens per session scan A 1ba4cd913281

Subscribe to this mod's changes

resume-writer is an agent published in the GitHub repository jananthan30/Resume-Builder (76 stars, last pushed 17d ago), licensed MIT. It adds 18 tokens to every session and 961 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

gemini-research-expert

Use this agent when the user needs to perform research tasks, gather information from external sources, or investigate topics that require web searches and synthesis of information.

MadsLorentzen/ai-job-search · 37 tokens

role-tailorer

Tailors one job end-to-end in a clean context — parse JD, build the coverage matrix, draft an ATS-safe CV from the master profile, write the cover letter and the L2 CV, file the folder + tracker row. Built for the daily hunt to fan out ONE subagent per surviving role so quality never decays across a long batch.…

soheilfallah/jobxhunter · 84 tokens

recruiter-critic

Independent recruiter persona that scores a tailored CV against a job description on the jobxhunter recruiter rubric. Give it ONLY the JD and the rendered CV — never the tailorer's notes — so its judgement can't be biased by the writer's rationale. Use it as the scoring half of the TAILOR recruiter loop and to score…

soheilfallah/jobxhunter · 76 tokens

career-doc-builder

Use this agent when the user needs to create, build, or update their Master Career Document (MCD). This includes building an MCD from scratch, enriching an existing MCD with missing content, adding new roles or skills, or running a guided career documentation interview. Examples of when to use this agent: User: "Help…

NullSpace-BitCradle/ats-resume-agent · 242 tokens

ats-resume-writer

Use this agent when the user needs to create, optimize, or revise a resume for job applications. This includes situations where: The user asks to create a resume from scratch The user wants to optimize an existing resume for ATS (Applicant Tracking Systems) The user needs to tailor a resume to a specific job…

NullSpace-BitCradle/ats-resume-agent · 398 tokens

company-facets

The denormalized facet columns on companies — job-derived remoteregions and curated yc columns — their maintenance, and the separation between the two.

strelov1/freehire · 0 tokens