bobbycode CLAUDE.md

bobbycode CLAUDE.md is an instructions file for coding agents from ccevans/bobbycode. It costs 3,719 tokens per session, scanned C, original, MIT.

A project instruction file for a codebase using Bobby, a ticket-based development workflow. It records the project's technology, commands, ticket locations, workflow stages, and safety rules.

In plain words
What is it for?
Use it to follow the project's task lifecycle, run its tests and lint checks, find tickets, and apply repository-specific safety requirements.
Why use it?
It gives coding agents and developers one place to learn how the repository is organized and how work should proceed.

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/ccevans/bobbycode/claude-md
Clone the repo
git clone --depth 1 https://github.com/ccevans/bobbycode

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 bobbycode CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ccevans/bobbycode/claude-md.svg)](https://agentmods.dev/instructions/ccevans/bobbycode/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ccevans/bobbycode/claude-md"><img src="https://agentmods.dev/badge/instructions/ccevans/bobbycode/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,719 This file is loaded in full into every session.
When invoked 3,719 The same file — it is already loaded in full.
Security scan C 1 finding. 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 $0.03719 $0.03719
Opus 5 $0.01860 $0.01860
Sonnet 5 $0.00744 $0.00744
Haiku 4.5 $0.00372 $0.00372

Measured yesterday against content hash a3f93dc59efb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

bobbycode CLAUDE.md scanned grade C with 1 finding 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- `rm -rf` or `rm -r` on directories outside the ticket's scope
CLAUDE.md · 302 lines

How it starts

The opening of the file, as written. The whole thing — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.

bobbycode — Bobby Workflow

This file was generated by bobby init. It tells Claude Code how to work with your project using Bobby's structured workflow.

Project

  • Name: bobbycode
  • Stack: generic
  • Tickets: .bobby/tickets/

Health Checks

Before starting work, verify the dev environment is running:

  • No health checks configured. Add them to .bobbyrc.yml.

Feature Areas

targets | dashboard | audit | tickets | packs | templates | cli

Commands

  • Test: npm test
  • Lint: npm run lint

Workflow

Bobby uses a ticket-based workflow with frontmatter-based stages:

backlog → planning → building → reviewing → testing → shipping → done

Tickets live in .bobby/tickets/ — stage is tracked in ticket.md frontmatter. Blocked tickets have blocked: true in frontmatter with a reason.

Safety Rules

<safety_rules> All agents must follow these rules. Violations are treated as critical failures.

Never run destructive commands:

  • rm -rf or rm -r on directories outside the ticket's scope
  • DROP TABLE, DROP DATABASE, TRUNCATE or any destructive SQL
  • git push --force or git push -f (use --force-with-lease if rebase is needed)
  • git reset --hard (use git stash or git checkout -- <file> for targeted reverts)
  • git clean -fd or git clean -fx
  • docker system prune, docker volume rm
  • kill -9 on unknown processes
  • chmod -R 777 or chown -R on system directories
  • Any command with sudo unless the plan explicitly requires it

Never modify outside your scope:

  • Do not edit files unrelated to the current ticket
  • Do not change CI/CD configuration unless the ticket explicitly requires it
  • Do not modify environment files (.env, credentials, secrets)
  • Do not install global packages or change system-level config

Always verify before acting:

  • Run git diff --stat before committing to review what changed
  • Run tests before marking work complete
  • Check git status after every commit to confirm clean state </safety_rules>

Read the full file on GitHub · 302 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 · 302 lines · 3,719 tokens per session scan C a3f93dc59efb

Subscribe to this mod's changes

bobbycode CLAUDE.md is an instructions file published in the GitHub repository ccevans/bobbycode (6 stars, last pushed 10d ago), licensed MIT. It adds 3,719 tokens to every session, about $0.0186 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.