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/random6913/claude-code-superkit/claude-mdgit clone --depth 1 https://github.com/RaNDoM6913/claude-code-superkitWhat 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 | $0.04184 | $0.04184 |
| Opus 5 | $0.02092 | $0.02092 |
| Sonnet 5 | $0.00837 | $0.00837 |
| Haiku 4.5 | $0.00418 | $0.00418 |
Grade A, and why
claude-code-superkit 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 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.
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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
claude-code-superkit
Production-tested agents, commands, hooks & skills for Claude Code and Codex CLI. All agents on Opus.
Project Structure
packages/
core/ # Generic components (any project)
agents/ # 31 agents (all opus) · incl. v1.4.0: minimal-change-engineer, reality-checker, codebase-onboarding-engineer, behavioral-nudge-engine
commands/ # 15 commands (+ 1 frontend-3d = 16 total)
hooks/ # 26 shipped + 2 superkit-internal = 28 files (27 *.sh + 1 *.py). Shipped incl. /dev trio, audit-settings-source (CVE-2025-59536), audit-trail, plan-completion-gate, user-intent-detect, subagent-stop-validate, compact-state-inject, edit-streak-check, intake-classifier.py, gateguard-pre-edit, gateguard-record-facts
helpers/ # 1 helper (statusline.cjs)
rules/ # 8 rules (+1 superkit-internal)
skills/ # 11 skills · incl. v1.4.0: telegram-bot-builder, nextjs-supabase-auth, drizzle-orm-expert, ru-text, postgresql-optimization, redis-patterns
INTERNAL-FILES # repo-only skip manifest (feeds installer / counts gate / updater)
settings.json # Hook wiring + statusLine
CLAUDE.md # Template for users
docs-templates/ # Architecture doc templates
stack-agents/ # Language-specific reviewers
go/ # go-reviewer + 5 specialized (error, concurrency, performance, modernizer, observability)
references/ # 34 Go knowledge documents (+5 in v1.4.0: di-frameworks, graphql-patterns, module-management, stay-updated, standard-stdlib-now; +5 in v1.5.1: refactoring-mechanics, cli-cobra-viper, gopls-driving, rest-openapi-patterns, troubleshooting)
typescript/ # ts-reviewer
python/ # py-reviewer
rust/ # rs-reviewer
stack-hooks/ # Language-specific hooks
go/ # format-on-edit, go-vet-on-edit + 4 new (error-check, context-check, safety-check, golangci-lint)
typescript/ # typecheck-on-edit
python/ # ruff-on-edit
rust/ # cargo-check-on-edit
stack-rules/ # Language-specific rules
go/ # go-conventions, go-safety
frontend-3d/ # Self-contained Frontend/3D/Animation package
agents/ # 4 agents (presentation-reviewer, r3f-scene-reviewer, ui-design-reviewer, frontend-perf-reviewer)
hooks/ # 4 hooks (gsap-pattern-check, r3f-color-check, tailwind-version-guard, bundle-size-warn)
skills/ # 6 skills (threejs-color-management, r3f-scroll-driven-3d, gltf-debugging, html-to-3d-texture, product-3d-lighting, output-enforcement)
rules/ # 3 rules (gsap-conventions, threejs-conventions, frontend-aesthetics-3d)
commands/ # 1 command (capture-screen)
README.md # Package documentation
frontend-ui/ # Self-contained Frontend 2D UI package (typography, color, motion, interaction)
agents/ # 6 agents (ui-reviewer umbrella + typography / color / motion / interaction / design-critic)
hooks/ # 3 hooks (ui-banned-fonts-check, ui-color-check, ui-animation-easing-check) + tests/
skills/ # 1 skill (impeccable-craft, opt-in shape-then-build flow)
rules/ # 7 rules (frontend-design-aesthetics, typography, color, spatial, motion, interaction, anti-patterns) — all applyWhenPaths-scoped
NOTICE.md # Apache-2.0 attribution for pbakaus/impeccable material
README.md # Package documentation
gan/ # NEW v1.4.0 — adversarial verification harness (optional, Playwright required)
agents/ # 3 agents (gan-planner, gan-generator, gan-evaluator)
skills/ # 3 Codex SKILL.md mirrors
rubrics/ # 2 rubric files (ui-quality, functionality)
README.md
extras/ # Optional components (require specific setup)
bot-reviewer.md # Telegram/Discord/Slack bot review
design-system-reviewer.md
red-blue-auditor.md
skillsmp-search/ # SkillsMP API search (requires API key)
codex/ # Codex CLI support
skills/ # 82 skills (added: 3 cross-CLI roles, 6 TGApp skills, behavioral-nudge, 3 GAN, silent-failure-hunter expansion)
rules/ # NEW v1.4.0 — default.rules DSL (Codex approval policy)
config.toml # gpt-5.5, xhigh
AGENTS.md # Template (incl. new "Approval Rules" section)
INSTALL.md # Guide
showcase/ # Production example (28 agents, 17 commands, 13 hooks, 11 skills, 6 rules)
.claude/ # Full .claude/ setup from real social app
setup.sh # POSIX wrapper → `node bin/cli.js`
bin/
cli.js # CLI entry point (#!/usr/bin/env node)
lib/
installer.js # Main orchestrator
prompts.js # Interactive prompts (readline)
settings-builder.js # JSON assembly (replaces jq)
superpowers.js # Plugin installation
docs-scaffold.js # Doc templates + tree
codex.js # Codex CLI support
validator.js # Post-install validation
utils.js # Colors, file helpers, git
test/
utils.test.js # Unit tests
settings-builder.test.js # Unit tests
smoke.test.js # Full install smoke test
package.json # npm package config
docs/
guide/ # 13 chapters
examples/ # 3 examples
INSTALL-CLAUDE-CODE.md # Detailed install guide
dev-flow.svg # Hand-authored /dev flow diagram used in README
dev-flow-variants/ # 4 alternative SVG layouts (timeline, radial, waterfall, node graph)
README.md
CHANGELOG.md
TROUBLESHOOTING.md
VERSION # current release version (keep in sync with package.json)
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.
- yesterday First seen · 244 lines · 4,184 tokens per session scan A 80b1edc21e87
claude-code-superkit CLAUDE.md is an instructions file published in the GitHub repository RaNDoM6913/claude-code-superkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 4,184 tokens to every session, about $0.0209 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.
Other instructions, from other repositories
apm tests.instructions.md
Test conventions: URL assertions must use urllib.parse, never substring.
apm cli.instructions.md
CLI Design Guidelines for visual output, styling, and user experience standards.
apm integrators.instructions.md
Architecture rules for file-level integrators (BaseIntegrator pattern).
apm copilot-instructions.md
Instructions for microsoft/apm, covering linting (canonical contract), ci-mirror commands, local workflow, common surprises and lifecycle binding.
apm architecture.instructions.md
Single canonical owner discipline: one authority per durable decision, guarded by a regression test + a static boundary check.
apm cicd.instructions.md
CI/CD Pipeline configuration for PyInstaller binary packaging and release workflow.