An autonomous job-application agent that searches for jobs, evaluates their fit, adapts CVs and cover letters, completes applications, and tracks results. It uses stored profile information and reports progress through Telegram.

Finding suitable jobs, scoring listings, tailoring application materials, submitting applications, handling unanswered questions, and maintaining an application ledger.

It organizes the full application process and keeps a record, while asking the user only for missing information it cannot answer.

jobpilot — Skill for Claude Code and Codex by fthsrbst

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.

Any agent

npx skills add fthsrbst/mnema --skill jobpilot

Clone the repo

git clone --depth 1 https://github.com/fthsrbst/mnema

Made for: Claude Code, Codex.

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/fthsrbst/mnema/jobpilot/github.svg)](https://agentmods.dev/skills/fthsrbst/mnema/jobpilot)

Your own site

<a href="https://agentmods.dev/skills/fthsrbst/mnema/jobpilot"><img src="https://agentmods.dev/badge/skills/fthsrbst/mnema/jobpilot/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/fthsrbst/mnema/jobpilot"><img src="https://agentmods.dev/badge/skills/fthsrbst/mnema/jobpilot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,582 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00056	$0.04582
Opus 5	$0.00028	$0.02291
Sonnet 5	$0.00011	$0.00916
Haiku 4.5	$0.00006	$0.00458

Measured 8d ago against content hash 3e7b661996da, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

jobpilot 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 8d 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.

skills/jobpilot/SKILL.md · 341 lines

How it starts

The opening of the file, as written. The whole thing — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.

JobPilot - Autonomous Job Application Agent (v2.0.0)

1. Identity & Mission

You are JobPilot, Fatih's personal job-application agent. Your mission:

Discover relevant job postings - globally and in Turkey.
Score each posting against Fatih's profile and preferences.
Tailor his CV and, when needed, write a custom cover letter - truthfully.
Apply, filling every form field from his knowledge base.
Learn: any question you cannot answer gets asked to Fatih exactly once via Telegram, then saved permanently to the Mnema hub RAG.
Report everything through Telegram and keep a complete application ledger in the hub.

Optimize for interview rate, not application count. Ten sharp applications beat fifty sloppy ones.

2. Runtime & Tool Mapping

You may be running inside Hermes agent on the Raspberry Pi or inside Claude Code / Cowork on desktop. Both connect to the same Mnema hub MCP server - that hub is your single source of truth. Detect what is available and map capabilities:

Capability	Hermes (Pi)	Claude Code / Cowork
Browser	local Chrome via CDP-attach (preferred) or built-in browser	Playwright MCP or claude-in-chrome
Persistent memory	`hub` MCP tools (`memory_`, `rag_`, `project_*`, `session_log`)	same `hub` MCP tools
User messaging	Telegram gateway - `clarify` tool with inline buttons for decisions, plain messages for reports	see Telegram fallback below
Scheduling	Hermes cron (jittered - see section 13)	harness scheduling tools
Code execution	terminal / Python RPC	Bash/PowerShell

Telegram fallback (desktop runtime): if the current runtime has no Telegram-sending capability, do not approximate the approval flow in a chat window Fatih may not be watching. Instead: queue the approval request into the hub project map next_steps (full request text, short id, timestamp) and state it in your session output. The Hermes runtime flushes this queue to Telegram at its next run (section 17.2). Never auto-submit anything whose approval you could not actually deliver.

Read the full file on GitHub · 341 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.

8d ago First seen · 341 lines · 56 tokens per session scan A 3e7b661996da

Subscribe to this mod's changes

jobpilot is a skill published in the GitHub repository fthsrbst/mnema (2 stars, last pushed 9d ago), licensed MIT. It adds 56 tokens to every session and 4,582 once invoked, about $0.0003 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.

Productivity ai-agents claude cli codex local-first mcp

reflect

Use Recall Reflect to review AI coding workflow history as a conversation-first timeline and discuss observed patterns before changing behavior. Trigger when the user asks to reflect on a project, review AI coding workflow, inspect workflow friction, discuss repeated corrections, review handoffs, or explore possible…

samzong/Recall · 57 tokens

anyr

Use when reading, searching, creating, or updating Anytype documents (objects, spaces, types, properties, files, chats) from the command line with the configured anyr CLI, including JSON output patterns for scripting.

stevelr/anytype · 46 tokens

day-log

Quick timestamped log entry — no conversation, just capture.

mpazik/Binder · 15 tokens

any-mcp

Use when an agent needs to read, search, create, edit, organize, upload, or chat with Anytype through the bounded any-mcp server. Covers safe tool selection, exact identifier chaining, optional toolsets, common PKM workflows, and the narrow anyr fallbacks for chat subscriptions and rich chat blocks.

stevelr/anytype · 68 tokens

anytype-setup

Install anyr and configure desktop or headless Anytype access. Use for authentication, endpoint selection, recovery, or limiting model-visible data with a dedicated headless account invited only to a sharing space; not ordinary object workflows.

stevelr/anytype · 50 tokens

period-summary

Period summary (w/m/q/y) — reflect on the period, score it, close it out.

mpazik/Binder · 24 tokens