jobclaw-skills: Instructions file for Codex

AGENTS.md

jobclaw-skills AGENTS.md is an instructions file for Codex, OpenCode from jain777/jobclaw-skills. It costs 1,219 tokens per session, scanned A, original, MIT.

A set of 20 portable instructions for coding agents that supports an end-to-end job search, from setting up a candidate profile and finding suitable jobs to preparing applications, interviews, and salary negotiations.

In plain words
What is it for?
Use it to search and score jobs, tailor resumes, write cover letters, answer application questions, manage recruiter messages, prepare for interviews, and practise negotiation.
Why use it?
It organizes many job-search tasks into reusable skills that work across different agent tools. Most tasks need no external service key, while job searching and company research can use optional data APIs.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

This is jain777/jobclaw-skills's own configuration. It tells Codex and OpenCode how to work on jobclaw-skills itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything jobclaw-skills configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jain777/jobclaw-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jain777/jobclaw-skills/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/jain777/jobclaw-skills

Made for: Codex, OpenCode.

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 jobclaw-skills AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jain777/jobclaw-skills/agents-md/github.svg)](https://agentmods.dev/instructions/jain777/jobclaw-skills/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/jain777/jobclaw-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/jain777/jobclaw-skills/agents-md/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.

agentmods 80×15 button for jobclaw-skills AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jain777/jobclaw-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/jain777/jobclaw-skills/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,219 This file is loaded in full into every session.
When invoked 1,219 The same file — it is already loaded in full.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01219 $0.01219
Opus 5 $0.00609 $0.00609
Sonnet 5 $0.00244 $0.00244
Haiku 4.5 $0.00122 $0.00122

Measured 10d ago against content hash c3f4a129aa0e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

jobclaw-skills AGENTS.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 10d 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.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — JobClaw by whatNxtAI

Universal, runtime-neutral instructions for any coding/agent runtime that reads AGENTS.md (Codex, Cursor, Hermes, OpenClaw, and friends). Claude Code reads CLAUDE.md; both point at the same skills. For per-runtime setup, see docs/RUNTIMES.md.

What this repo is

JobClaw by whatNxtAI is a collection of 20 portable Agent Skills that run an end-to-end job hunt — onboarding a profile, searching jobs, scoring fit, tailoring resumes, writing cover letters, answering application questions, triaging the recruiter inbox, prepping interviews, and coaching negotiation — plus shared knowledge packs. The LLM is the engine: ~14 of the 20 skills are pure reasoning and need no external API key. Only job search and company research use optional data-API keys (copy .env.example.env).

These skills are runtime-agnostic. Each is a SKILL.md directory under skills/, written to the open agent-skills standard (name + description frontmatter, markdown body, optional scripts/ and reference/). Nothing here depends on a specific agent framework.

How skills work here

  • Discovery / invocation. Skills live in skills/<verb-noun>/SKILL.md. Invoke one when the task matches its description (auto), or explicitly by name. Each skill ends by naming the next step in the pipeline. Cross-runtime discovery paths and invocation syntax are in docs/RUNTIMES.md.
  • Composition is file-based, not call-based. Skills do not invoke each other through a framework API. They compose via small JSON sidecars at fixed paths and one shared master profile — so the chain works identically on any runtime. The full stage map is in knowledge/pipeline.md. Key sidecars:
    • profile/master-profile.md — the shared memory build-profile writes and every skill reads.
    • jobs/current.json — the job under work ({company, role, url, job_id, jd_text, region, …}).
    • scores/<job-id>.score.jsonscore-fittailor-resume.
    • resumes/<slug>.tailor.jsontailor-resumewrite-cover-letter.
    • companies/<slug>.jsonresearch-companyprep-interview / coach-negotiation.
    • inbox/triage-<YYYY-MM-DD>.jsontriage-inboxinfer-status / draft-reply.
  • Scripts. Thin Python 3 stdlib-only helpers under skills/*/scripts/ — run them with python3. They print JSON to stdout, read keys from env, and degrade gracefully (never crash) when a key or dependency is missing. The one exception is render-resume, which uses rendercv in its own .venv (optional; install only if you need resume PDFs). Run python3 scripts/doctor.py to see what's installed.

Read the full file on GitHub · 73 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. 10d ago First seen · 73 lines · 1,219 tokens per session scan A c3f4a129aa0e

Subscribe to this mod's changes

jobclaw-skills AGENTS.md is an instructions file published in the GitHub repository jain777/jobclaw-skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 1,219 tokens to every session, about $0.0061 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens