careerops

A career-planning assistant that works from a user's resumes, accomplishments, portfolio, or exported career data. It supports modes for reviewing opportunities, tailoring materials, interview preparation, follow-up, and career advice.

In plain words
What is it for?
Use it to evaluate and rank roles, tailor resumes or other materials, prepare for interviews, draft follow-ups, track outcomes, and organize verified career evidence.
Why use it?
It keeps career materials grounded in the user's real experience instead of inventing employers, dates, skills, or results. It also leaves applications and messages for the person to submit themselves.

Skill for Claude CodeCodex

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/telivityai/careerops/skill
Any agent
npx skills add TelivityAI/careerops --skill skill
Clone the repo
git clone --depth 1 https://github.com/TelivityAI/careerops

Made for: Claude Code, Codex.

Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 847 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00044 $0.00847
Opus 5 $0.00022 $0.00424
Sonnet 5 $0.00009 $0.00169
Haiku 4.5 $0.00004 $0.00085

Measured 3d ago against content hash 6350f51c0459, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

careerops 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.

Origin

This is a copy

100% identical to careerops — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

packages/careerops/skill/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CareerOps skill

Career OS — operate on the user's board pack (exported JSON from the CareerOps web app) or their self-hosted Supabase project.

Doctrine (non-negotiable)

  1. No invented facts — employers, titles, dates, metrics, and skills must come from the user's materials / bullet memory / portfolio.
  2. No auto-apply / no auto-send — drafts are copy/paste only; the human submits on the employer site and sends their own mail.
  3. Tags ≠ stage moves — Apply / Stretch / Skip are suggestions until the user acts.
  4. Memory provenancebody_original is immutable; AI polish requires Accept; promotion is bidirectional (source_type / source_id ↔ accomplishment links).
  5. resume_struct is canonical — promotion and portfolio promote go through one atomic write that syncs resume_text (never silent dual-write divergence).
  6. Generate retrieval — checked → role-linked → relevance → recency tie-break only (not newest-20).
  7. Enrichment = inbox + Accept — GitHub/LinkedIn (and similar) proposals land as candidates; never silent scrape into resume.
  8. Deferred forever (unless doctrine changes) — auto-apply, auto-send, silent scrape into resume, invented salary bands, ungated multi-agent writes of experience without accept.

See docs/DOCTRINE_MEMORY.md and docs/ROADMAP.md in the CareerOps repo.

Modes

Mode Purpose
scan Review sourced roles; flag blocklist, age, remote, duplicates
evaluate Build a decision pack (summary, risks, suggested call)
rank Order roles by fit signals without applying
tailor Draft resume/cover from checked / ranked materials only
interview Prep angles + story-bank prompts (roadmap: durable interview events)
followup Draft follow-up / thank-you notes (never send)
outcome Record offer/reject notes (roadmap: structured offer fields via pack)
advise Structured career advisor brief — materials-only past; labeled market judgment

Read the full file on GitHub · 62 lines

Files

What ships with it

8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 62 lines · 44 tokens per session scan A 6350f51c0459

Subscribe to this mod's changes

careerops is a skill published in the GitHub repository TelivityAI/careerops (53 stars, last pushed 9d ago), licensed Apache-2.0. It adds 44 tokens to every session and 847 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to careerops, differing in 0 lines, and is treated as a copy.