agentmods.dev

jobpilot CLAUDE.md

A set of project instructions for Claude Code, an AI coding assistant, working on the JobPilot application. It describes the repository layout, development services, authentication flow, and rules for different parts of the codebase.

In plain words
What is it for?
Use it as a reference when working on the web app, API, local .NET terminal host, shared packages, authentication, or development commands.
Why use it?
It gives the coding assistant the project context needed to make changes in the right application, service, and folder.

Instructions file

60 11d ago A scan 963 tokens original MIT
View the source file suxrobGM/jobpilot
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 instructions/suxrobgm/jobpilot/claude-md
Clone the repo
git clone --depth 1 https://github.com/suxrobGM/jobpilot
Per session 963 This file is loaded in full into every session.
When invoked 963 The same file — it is already loaded in full.
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 $0.00963 $0.00963
Opus 5 $0.00481 $0.00481
Sonnet 5 $0.00193 $0.00193
Haiku 4.5 $0.00096 $0.00096

Measured yesterday against content hash 488e99fed731, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

jobpilot CLAUDE.md 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.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

JobPilot

Multi-user AI job-application app. The Next.js web UI and the Elysia + PostgreSQL API (owner of all state) are cloud-hosted and shared across users; each user runs the agent locally - Claude Code or Codex in a .NET PTY host, plus Playwright - so jobs run on that user's own subscription. Dev ports: web :4100, API :4101, PTY host :4102.

Auth: on terminal start the web fetches the user's reusable terminal token (POST /api/auth/tokens/terminal) and hands it to the PTY host, which injects it as JOBPILOT_API_TOKEN; skills send it as Authorization: Bearer to the API.

Layout

  • apps/web/ - Bun + Next.js 16 + MUI 9 UI; talks to the API over HTTP only (no direct DB). Browser and server hit Elysia directly via NEXT_PUBLIC_API_URL - src/proxy.ts is Next 16 auth middleware (route gating), not a data proxy.
  • apps/api/ - Bun + Elysia + Prisma 7; owns all persistence. Exports type App for Eden Treaty typing; Swagger UI at :4101/swagger in dev.
  • apps/terminal/ - .NET 10 PTY host (JobPilot.Terminal); runs on each user's machine.
  • tests/JobPilot.Terminal.Tests/ - .NET test suite for the host (solution: JobPilot.slnx).
  • packages/ - @jobpilot/contracts (shared Zod schemas), @jobpilot/api-client (Eden client).
  • plugin/ - the JobPilot plugin: one provider-neutral skill tree for Claude and Codex. Edit skills here directly - no generation step.
  • docs/ - user-facing docs; deploy/ - production stack.

Commands

Root (bun run …):

  • dev - terminal + api + web together; dev:api / dev:web / dev:terminal run one.
  • db:tunnel - SSH tunnel to the remote PostgreSQL, bound to localhost:5433. The repo ships no database container, so DATABASE_URL points at whichever PostgreSQL you supplied - a local one you run yourself or the tunnel. Both conventionally use 5433, so check what is actually on that port (docker ps, lsof -i :5433) before concluding which you are talking to.
  • db:setup - Prisma generate + apply migrations + seed.
  • test - the API suite plus the contracts suite (bun test in apps/api and packages/contracts).
  • build:api / build:web / build:terminal - production builds.
  • check / format / lint - Biome repo-wide (check = format + lint + import sort, writes). Biome skips Markdown; .editorconfig covers whitespace there.
  • ci - biome ci --error-on-warnings .. Warnings must fail the build or the gate is a no-op. Never run biome check --write --unsafe: the noNonNullAssertion fix rewrites cookie[KEY]!.set(…) to ?.set(…), silently dropping auth cookie writes.

Read the full file on GitHub · 63 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 · 63 lines · 963 tokens per session scan A 488e99fed731

Subscribe to this mod's changes

jobpilot CLAUDE.md is an instructions file published in the GitHub repository suxrobGM/jobpilot (60 stars, last pushed 11d ago), licensed MIT. It adds 963 tokens to every session, about $0.0048 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.

Backend and APIsBrowser automationResearchautomationclaude-codeclaude-code-plugincover-letterjob-applicationjob-search
Related

Other instructions, from other repositories

job-seeker AGENTS.md

Instructions for galiprandi/job-seeker, covering job seeker — rules, gold rules, gold rule 1, gold rule 2 and gold rule 3 — user preferences always up to date.

galiprandi/job-seeker · 8,384 tokens

dear-hiring-manager CLAUDE.md

Instructions for extrasmall0/dear-hiring-manager, covering claude.md — dear-hiring-manager, what this is, architecture principle, layout and user data (never in repo).

extrasmall0/dear-hiring-manager · 1,005 tokens

give-me-job AGENTS.md

Instructions for kyoungbinkim/give-me-job, covering give-me-job repository instructions, default workflow, skill routing, working on this repository and development loop.

kyoungbinkim/give-me-job · 1,106 tokens

job-search AGENTS.md

Instructions for pedrolucazx/job-search, covering job search agent, where to start, repository conventions and if your agent has no slash commands.

pedrolucazx/job-search · 840 tokens

claude-resume-kit CLAUDE.md

Instructions for ARPeeketi/claude-resume-kit, covering claude-resume-kit — project instructions, file map, your role, user focus directives and anti-fabrication rules.

ARPeeketi/claude-resume-kit · 1,387 tokens

resume-tailor-plugin CLAUDE.md

Instructions for olegvg/resume-tailor-plugin, covering claude.md, project overview, architecture, key concepts and external dependency.

olegvg/resume-tailor-plugin · 636 tokens