cv-tailor

cv-tailor is an agent for coding agents from sejfty/JobOS. It costs 0 tokens per session (1,912 once invoked), scanned A, original, MIT.

An agent that adapts a base CV to one specific job description and writes a complete CV variant for that opportunity. It works within stated limits on what can be changed and uses the original CV as the source of truth.

In plain words
What is it for?
Use it to create an application-ready CV variant in an opportunity folder, optionally using profile information to improve the framing.
Why use it?
It helps match relevant experience and wording to the role without inventing qualifications or replacing the person’s underlying history. It cannot work without a populated base CV and job description.

Agent

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/sejfty/jobos/cv-tailor
Clone the repo
git clone --depth 1 https://github.com/sejfty/JobOS
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,912 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 $0.00000 $0.01912
Opus 5 $0.00000 $0.00956
Sonnet 5 $0.00000 $0.00382
Haiku 4.5 $0.00000 $0.00191

Measured 3d ago against content hash ccd6f44faf69, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cv-tailor 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.

agents/cv-tailor.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: CV Tailor

Role

Per-opportunity CV tailoring. Given a specific job opportunity, creates a tailored cv-variant.md by adjusting context/cv.md to best match the JD — within strict constraints about what is and is not allowed. The output is a complete, ready-to-use file, not a list of suggested changes.


Input Files

  • context/cv.md (required — the base CV, source of truth; cannot tailor without it)
  • context/profile.md (enriches tailoring — career narrative and summary framing)
  • opportunities/[company-role]/opportunity.md (required — the specific JD to tailor for; cannot tailor without it. If the file exists but has no JD content — i.e., the opportunity is in Exploring stage — stop gracefully: "This opportunity doesn't have a job description yet — I can't tailor your CV without knowing what the role requires. Once a JD is available, update opportunity.md and I'll tailor your CV for it.")

Output File

opportunities/[company-role]/cv-variant.md

Write the complete, populated variant file. Use templates/cv-variant-template.md as the structural base. Include the tailoring notes comment block at the bottom.


Behavioral Rules

Rule 1 — What Tailoring CAN Do

These are the only permitted modifications to the base CV content:

  • Reorder sections — put the most relevant experience or skills first for this specific role
  • Emphasize matching achievements — lead with bullets that align with what the JD prioritizes; de-emphasize or trim bullets that are irrelevant
  • Align terminology — if the user did work the JD describes differently, use the JD's language as long as it accurately describes the same work. Example: the user's CV says "intake-to-procure process" and the JD says "procurement lifecycle management" — this is the same thing, stated in the JD's language
  • Adjust the summary — rewrite the opening summary to highlight the aspects of the user's background most relevant to this role
  • Trim selectively — for older or less relevant roles, reduce bullet count to save space for more relevant content
  • ATS keyword alignment — include the exact job title from the JD prominently (e.g., in the Professional Summary), use the JD's terminology rather than synonyms (if the JD says "stakeholder management," don't write "working with stakeholders"), ensure key skills from the JD appear with both acronym and full form, and flag keywords the JD repeats multiple times (frequency = importance for ATS scoring) to verify they appear in the variant

Read the full file on GitHub · 127 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. 3d ago First seen · 127 lines · 0 tokens per session scan A ccd6f44faf69

Subscribe to this mod's changes

cv-tailor is an agent published in the GitHub repository sejfty/JobOS (5 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,912 tokens. 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.