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/mikekelly/promode/claude-mdgit clone --depth 1 https://github.com/mikekelly/promodeWrote 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.
[](https://agentmods.dev/instructions/mikekelly/promode/claude-md)<a href="https://agentmods.dev/instructions/mikekelly/promode/claude-md"><img src="https://agentmods.dev/badge/instructions/mikekelly/promode/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.02119 | $0.02119 |
| Opus 5 | $0.01059 | $0.01059 |
| Sonnet 5 | $0.00424 | $0.00424 |
| Haiku 4.5 | $0.00212 | $0.00212 |
Grade A, and why
promode 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 5d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Keep this file under 50 lines. This is a plugin repository - see plugins/promode/ for the actual plugin.
What is Promode?
Promode is a Claude Code plugin whose main goal is to make Claude Code operate in an opinionated way that drives projects in the direction of its owner's preferences — spanning how the harness's features are used, product and engineering methodology, and knowledge/memory management. It ships:
- Agents — phase-specific subagents for hard-to-reverse design, implementation, review, debugging, verification/QA, environment management, product design, after-action analysis, methodology audit, and constraint reinforcement
- Commands — user-typed flows (
/promode:handoff,/promode:promode-audit); cross-cutting mechanics live in routed docs (plugins/promode/docs/) reached by def-directed reads. No skills, by design — voluntary invocation is non-determinate:docs/decisions/2026-07-skills-elimination.md
Core philosophy: TDD is non-negotiable, tests are the documentation, context is precious, discovery hardens into deterministic tests/scripts/maps, and the main agent orchestrates — and enforces the opinions — while subagents execute, instilled with the same opinions. Promode is intended to be forked per user — methodology is taste, this repo is the mikekelly fork — and the opinion register (imported below) is the single evolvable home of the owner's preferences and a fork's customisation surface: opinions evolve gradually, and changing one there then syncing its homes is what drives the change in the prompting and tools that carry it — the fork stays coherently yours.
Overriding design goal — optimise for the current harness. Promode's techniques target the latest Claude Code features/behaviour, and silently decay as the harness evolves. Two verification resources: the community-tracked Claude Code changelog for what changed release-to-release, and the harness you are running in (when you're a Claude Code agent working on this repo) — probe it live to verify undocumented behaviour and edge cases (how SendMessage steer/resume and hook chunking were pinned down) before building a technique on an assumption.
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.
- 5d ago First seen · 50 lines · 2,119 tokens per session scan A 82e267a336f9
promode CLAUDE.md is an instructions file published in the GitHub repository mikekelly/promode (21 stars, last pushed 1mo ago), licensed MIT. It adds 2,119 tokens to every session, about $0.0106 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
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).
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.
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.
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-release stance: foundation over blast radius, repository layout, commands and host sandbox failures.