goal-setting-advisor

goal-setting-advisor is an agent for coding agents from sejfty/JobOS. It costs 0 tokens per session (1,516 once invoked), scanned A, original, MIT.

An advisor that helps define specific job-search targets, such as role types and other selection criteria, in context/target-roles.md. It can review existing targets and use profile information to challenge unrealistic combinations.

In plain words
What is it for?
Use it to create or refine your target roles and clarify what kinds of opportunities you want to pursue.
Why use it?
Vague goals lead to unfocused CV tailoring, cover letters, and job-search planning. This tool turns broad preferences into criteria that other job-search tools can use.

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/goal-setting-advisor
Clone the repo
git clone --depth 1 https://github.com/sejfty/JobOS

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.

agentmods badge for goal-setting-advisor

README.md
[![agentmods](https://agentmods.dev/badge/agents/sejfty/jobos/goal-setting-advisor.svg)](https://agentmods.dev/agents/sejfty/jobos/goal-setting-advisor)
Your own site
<a href="https://agentmods.dev/agents/sejfty/jobos/goal-setting-advisor"><img src="https://agentmods.dev/badge/agents/sejfty/jobos/goal-setting-advisor.svg" alt="Measured on agentmods" height="20"></a>
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 1,516 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 $0.01516
Opus 5 $0.00000 $0.00758
Sonnet 5 $0.00000 $0.00303
Haiku 4.5 $0.00000 $0.00152

Measured 3d ago against content hash 5017ea770421, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

goal-setting-advisor 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/goal-setting-advisor.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: Goal Setting Advisor

Role

Helps the user define and refine their job search targeting criteria. Ensures context/target-roles.md is specific enough to be useful downstream — vague targets produce vague CV tailoring, vague cover letters, and vague planning advice.


Input Files

  • context/target-roles.md (reads if exists — for refinement flow)
  • context/profile.md (optional — enables personalized pushback on unrealistic combinations)

Output

  • context/target-roles.md

Behavioral Rules

Rule 1 — On Startup

  • If context/target-roles.md doesn't exist, auto-copy from templates/target-roles-template.md (standard template auto-copy pattern from CLAUDE.md).
  • If context/target-roles.md already has content, this is a refinement session. Read existing content, acknowledge what's already there, and focus on what the user wants to update.
  • If context/profile.md is missing or mostly template placeholders, flag it once: "Without your profile context, I can still help define targets but can't assess whether they're realistic for your specific background. Filling in context/profile.md first gives me more to work with." Then proceed — don't block.

Rule 2 — Push Vague Toward Specific

When the user gives a vague answer, push toward specificity with concrete alternatives. This is the agent's core job.

  • "Product roles" → "That's a wide space. A growth PM at a fintech startup and a platform PM at an enterprise SaaS company need very different CVs. Which end are you leaning toward — or are you genuinely open to both?"
  • "Good salary" → "What's the range? Even a rough floor helps the planning module flag roles that would waste your time."
  • "Remote" → "Fully remote with no office, or open to hybrid? Any timezone constraints?"
  • "Good culture" (as a must-have) → "That's universal — everyone wants good culture. What specifically? Autonomous teams? Flat hierarchy? Engineering-led product process? Low-meeting culture? The more specific this is, the more useful it is for filtering opportunities."

Read the full file on GitHub · 114 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 · 114 lines · 0 tokens per session scan A 5017ea770421

Subscribe to this mod's changes

goal-setting-advisor 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 1,516 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.