What is nextjobkit AGENTS.md?

Repository instructions for Next Job Kit, a tool that builds truthful, role-specific job application materials from a candidate’s evidence and resumes. They define which files are authoritative and how agents should choose the right workflow.

Use them when working on candidate profiles, resumes, tailored applications, or generated HTML and PDF materials, while keeping the configured evidence files as the source of truth.

They reduce the risk of inventing qualifications or using outdated application details. The source hierarchy tells agents which evidence to trust when documents disagree.

How farrelfatah/nextjobkit configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to farrelfatah/nextjobkit. 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/farrelfatah/nextjobkit/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/farrelfatah/nextjobkit

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/farrelfatah/nextjobkit/agents-md/github.svg)](https://agentmods.dev/instructions/farrelfatah/nextjobkit/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/farrelfatah/nextjobkit/agents-md"><img src="https://agentmods.dev/badge/instructions/farrelfatah/nextjobkit/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/farrelfatah/nextjobkit/agents-md"><img src="https://agentmods.dev/badge/instructions/farrelfatah/nextjobkit/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,969 This file is loaded in full into every session.

When invoked 1,969 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.

Model	Per session	Once invoked
Fable 5.1	$0.01969	$0.01969
Opus 5.5	$0.00788	$0.00788
Sonnet 5.5	$0.00394	$0.00394
Haiku 4.5	$0.00197	$0.00197

Measured 2mo ago against content hash 533fe3d3fc5c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

nextjobkit 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 2mo 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 · 216 lines

How it starts

The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Next Job Kit Agent Contract

Mission

Help a candidate build defensible, role-specific application packages from evidence. Optimize for truth, relevance, and usable artifacts—not résumé theater.

The workflow must remain portable to a newly initialized workspace even when the current workspace contains real candidate data.

Read First

profile/candidate.md — the only user-facing configuration and decision interface.
The configured evidence file.
The configured master resume.
The relevant job source and existing application artifacts.

Resolve canonical paths and the selected template from the profile. Do not hardcode a person's name, slug, role, or filenames in workflow logic.

Source Hierarchy

When facts conflict, use this order:

Direct user confirmation and primary evidence.
The configured resume evidence file.
The configured master resume.
Tailored and application artifacts.
Generated HTML and PDF.

Markdown is canonical. HTML, PDF, DOCX, and form entries are delivery artifacts unless the user explicitly says otherwise.

Skill Router

Use the smallest skill that owns the current stage:

Need	Skill
Personalize or repair a workspace	`setup-resume-workspace`
Missing facts, outcomes, or direction	`discover-resume-evidence`
Requirements, eligibility, and fit	`analyze-job-fit`
Targeted resume version	`tailor-resume`
Cover letter or hiring-manager note	`write-cover-letter`
Content, ATS, and PDF QA	`audit-resume`
Interview brief and story bank	`prepare-interview`

Do not invoke the entire chain for a narrow task. Evidence discovery is conditional, not ritual. Cover letters are part of the core package when the application benefits from one.

Default Workflow

profile/candidate.md
        ↓
confirmed evidence
        ↓
master resume
        ↓
job-fit analysis
        ↓
tailored resume → cover letter → audit/export
        ↓
application tracker
        ↓
interview preparation

Read the full file on GitHub · 216 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.

2mo ago First seen · 216 lines · 1,969 tokens per session scan A 533fe3d3fc5c

Subscribe to this mod's changes

nextjobkit AGENTS.md is an instructions file published in the GitHub repository farrelfatah/nextjobkit (5 stars, last pushed 16d ago), licensed MIT. It adds 1,969 tokens to every session, about $0.0079 per session on Opus 5.5. 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.

Writing and docs

nextjobkit AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
nextjobkit AGENTS.mdfarrelfatah/nextjobkit	Instructions file	5	16d ago	MIT	A	1,969	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

nextjobkit: Instructions file for Codex