github-resume-assistant CLAUDE.md

github-resume-assistant CLAUDE.md is an instructions file for coding agents from justomsharma/github-resume-assistant. It costs 885 tokens per session, scanned A, original, MIT.

Project instructions for GitHub Resume Assistant, an MCP server that uses a person's real GitHub activity to suggest public projects and improve resume credibility.

In plain words
What is it for?
Use them when working on this project to choose the right skill, understand its product scope, locate its documentation, and follow its architecture, coding, and testing practices.
Why use it?
They tell the coding agent which project documents and rules to follow, including how to handle users with little or no GitHub activity.

Instructions file

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/justomsharma/github-resume-assistant/claude-md
Clone the repo
git clone --depth 1 https://github.com/justomsharma/github-resume-assistant

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 github-resume-assistant CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/justomsharma/github-resume-assistant/claude-md.svg)](https://agentmods.dev/instructions/justomsharma/github-resume-assistant/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/justomsharma/github-resume-assistant/claude-md"><img src="https://agentmods.dev/badge/instructions/justomsharma/github-resume-assistant/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 885 This file is loaded in full into every session.
When invoked 885 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 $0.00885 $0.00885
Opus 5 $0.00443 $0.00443
Sonnet 5 $0.00177 $0.00177
Haiku 4.5 $0.00089 $0.00089

Measured 3d ago against content hash 1ea3493e2b0b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

github-resume-assistant 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 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.

CLAUDE.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — GitHub Resume Assistant

Read this at the start of every session. It tells you what we're building, the rules to follow, and which skill to use when.

What this project is

An MCP server that connects Claude to a user's real GitHub activity and prescribes what to build and ship publicly to make their resume credible. The full spec is in docs/PRODUCT.md. Read it before making product decisions.

Key facts to internalize:

  • v1's only user is the builder (you). Not "everyone with a resume."
  • suggest_projects is the heart of the product; analyze_resume supports it.
  • The competitor is free ChatGPT copy-paste. We only win by grounding advice in real GitHub data.
  • The empty-GitHub case is the main case, not an edge case — handle it everywhere.

Documentation map (read the relevant one before acting)

Doc When to read
docs/PRODUCT.md Any product/scope decision
docs/ROADMAP.md Deciding what to build next; check version order
docs/ARCHITECTURE.md Before creating/moving any file
docs/CODING_PRACTICES.md Before/while writing code
docs/TESTING.md Before/while writing tests
docs/GIT_WORKFLOW.md Committing, pushing, PRs

The golden rule

Never write code before an approach is read, formed, and validated. Every coding request starts at /plan-first. No exceptions.

Skill routing — which skill, when

When the user's request matches a skill below, invoke it via the Skill tool. When in doubt on a coding task, start with /plan-first.

Situation Skill
User asks to add / change / fix / build anything /plan-first
An approach was just approved, time to write code /implement
Code was written, needs tests /test
Tests pass, review the diff before committing /self-review
Diff is clean, commit and push /commit-push
Branch pushed, open the PR/MR /open-pr
Review a PR/MR before merge /review-pr

Read the full file on GitHub · 78 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 · 78 lines · 885 tokens per session scan A 1ea3493e2b0b

Subscribe to this mod's changes

github-resume-assistant CLAUDE.md is an instructions file published in the GitHub repository justomsharma/github-resume-assistant (0 stars, last pushed 1mo ago), licensed MIT. It adds 885 tokens to every session, about $0.0044 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.