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.
npx agentmods add instructions/backspace-shmackspace/claude-devkit/claude-mdgit clone --depth 1 https://github.com/backspace-shmackspace/claude-devkitWhat 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 | $0.00945 | $0.00945 |
| Opus 5 | $0.00473 | $0.00473 |
| Sonnet 5 | $0.00189 | $0.00189 |
| Haiku 4.5 | $0.00094 | $0.00094 |
Grade A, and why
claude-devkit 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.
How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Devkit
Version: 1.0.0 Last Updated: 2026-08-21 Purpose: Unified development toolkit for Claude Code - skills, agents, generators, and templates
For full architecture, skill registry, workflows, and troubleshooting, see REFERENCE.md. For a getting-started tutorial, see GETTING_STARTED.md.
Coding Guidelines
These apply to all work in this project — interactive, headless, ad hoc, or skill-driven.
1. Think Before Coding
- State assumptions explicitly. If uncertain, ask.
- If multiple interpretations exist, present them — don't pick silently.
- If a simpler approach exists, say so. Push back when warranted.
- If something is unclear, stop. Name what's confusing. Ask.
2. Simplicity First
- No features beyond what was asked.
- No abstractions for single-use code.
- No "flexibility" or "configurability" that wasn't requested.
- No error handling for impossible scenarios.
- If you write 200 lines and it could be 50, rewrite it.
3. Surgical Changes
When editing existing code:
- Don't "improve" adjacent code, comments, or formatting.
- Don't refactor things that aren't broken.
- Match existing style, even if you'd do it differently.
- If you notice unrelated dead code, mention it — don't delete it.
When your changes create orphans:
- Remove imports/variables/functions that YOUR changes made unused.
- Don't remove pre-existing dead code unless asked.
Every changed line should trace directly to the request.
4. Goal-Driven Execution
Transform tasks into verifiable goals:
- "Add validation" -> "Write tests for invalid inputs, then make them pass"
- "Fix the bug" -> "Write a test that reproduces it, then make it pass"
- "Refactor X" -> "Ensure tests pass before and after"
5. Output Rules
- Always print full absolute paths for artifact references (plan files, review files, audit logs). Makes paths clickable in Warp terminal.
Project Rules
Python
- stdlib only for all scripts in
scripts/. No external dependencies. - Atomic writes via
_atomic_write_json()or temp-file-then-rename. - Validation tuples
(bool, error_msg)for validation functions.
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.
- 3d ago First seen · 116 lines · 945 tokens per session scan A a787c6044f20
claude-devkit CLAUDE.md is an instructions file published in the GitHub repository backspace-shmackspace/claude-devkit (15 stars, last pushed 9d ago), licensed MIT. It adds 945 tokens to every session, about $0.0047 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.
Other instructions, from other repositories
dotskills AGENTS.md
Instructions for vincentkoc/dotskills, covering agents.md, repository purpose, mandatory contribution flow, skill standards and openai metadata defaults.
FMT-exocortex-template CLAUDE.md
Claude Code instructions for TserenTserenov/FMT-exocortex-template, covering инструкции для всех репозиториев, 1. архитектура репозиториев, 2. орз-фрактал (открытие → работа → закрытие), блокирующие правила and протокол работы (полный → memory/protocol-work.md).
dxkit CLAUDE.md
Instructions for vyuh-labs/dxkit, covering claude.md — dxkit development rules, architecture rules, 1. tool invocation goes through the registry, 2. never duplicate tool invocation logic and 3. language facts come from detect.ts.
asap-protocol AGENTS.md
AGENTS.md instructions for asap-protocol/asap-protocol, covering agents.md, project context, quick start, agent guidance (rules vs skills) and knowledge map.
slipway AGENTS.md
Instructions for signalridge/slipway, covering slipway agent principles, user owns the process, investigate before clarifying, report, do not certify and maintain the whole surface.
ai-marketplace AGENTS.md
Instructions for Kong/ai-marketplace, covering skill authoring guide, what belongs here, before you create a skill, what a good skill does and layered skill design.