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/nklisch/claude-code-modes/claude-mdgit clone --depth 1 https://github.com/nklisch/claude-code-modesWrote 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/nklisch/claude-code-modes/claude-md)<a href="https://agentmods.dev/instructions/nklisch/claude-code-modes/claude-md"><img src="https://agentmods.dev/badge/instructions/nklisch/claude-code-modes/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 | $0.01879 | $0.01879 |
| Opus 5 | $0.00940 | $0.00940 |
| Sonnet 5 | $0.00376 | $0.00376 |
| Haiku 4.5 | $0.00188 | $0.00188 |
Grade A, and why
claude-code-modes 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 4d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
claude-code-modes
CLI launcher for Claude Code with behaviorally-tuned system prompts. See VISION.md, SPEC.md.
Repo: https://github.com/nklisch/claude-code-modes
Commands
bun test # run all tests
bun run src/build-prompt.ts --help # test CLI directly
bun run src/build-prompt.ts create --print # inspect assembled prompt
bun run src/build-prompt.ts config show # view current config
bun run src/cli.ts create # full e2e (needs claude installed)
bun scripts/bump-version.ts patch # bump version, commit, tag, push (triggers release CI)
Project Structure
src/
types.ts # all enums, types, interfaces — single source of truth
env.ts # system environment detection (git, platform, shell)
assemble.ts # manifest-driven prompt fragment assembly pipeline
presets.ts # preset name → AxisConfig mapping
args.ts # CLI arg parsing → ParsedArgs
resolve.ts # ParsedArgs + config → ModeConfig (axis/modifier/base resolution)
config.ts # .claude-mode.json loading, validation, collision checks
config-cli.ts # `claude-mode config` subcommand (init, show, add/remove)
inspect.ts # `claude-mode inspect` subcommand (fragment provenance, warnings)
update.ts # `claude-mode update` subcommand (self-update from GitHub Releases)
version-check.ts # auto update-check fired on cli.ts entry
cli.ts # main entry point: spawns claude with assembled prompt
build-prompt.ts # alternative entry: outputs claude command string for scripting
test-helpers.ts # shared test utilities (createCliRunner, makeTempDir, PROJECT_ROOT)
prompts/
base/ # standard base: base.json manifest + 10 fragments
chill/ # chill base: base.json manifest + 6 fragments (emotion-research-informed)
flow/ # flow base: base.json manifest + 6 fragments (chill's calm + restored engagement)
lean/ # lean base: base.json manifest + 6 fragments (upstream's lean assembly)
straight/ # straight base: base.json manifest + 6 fragments (direct, anti-sycophantic)
axis/ # 10 fragments: agency/{autonomous,collaborative,surgical,partner}, quality/{architect,pragmatic,minimal}, scope/{unrestricted,adjacent,narrow}
style/ # user-visible writing: declaudified.md, straight.md
modifiers/ # readonly.md, context-pacing.md, debug.md, methodical.md, director.md, bold.md, speak-plain.md, tdd.md, muse.md, flow.md, playful.md, delivering-work.md, corrections.md, tool-restraint.md
scripts/
generate-prompts.ts # embeds prompt fragments into src/embedded-prompts.ts
extract-upstream-prompt.ts # downloads CC npm package, extracts system prompt functions
upstream-prompts/ # (gitignored) extracted upstream prompts for diffing
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.
- 4d ago First seen · 125 lines · 1,879 tokens per session scan A 45ef76639b1c
claude-code-modes CLAUDE.md is an instructions file published in the GitHub repository nklisch/claude-code-modes (115 stars, last pushed 26d ago), licensed MIT. It adds 1,879 tokens to every session, about $0.0094 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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.