supertag-cli CLAUDE.md

Project instructions for supertag-cli, a command-line tool whose development follows written feature specifications. A command-line tool is operated by typing commands in a terminal.

In plain words
What is it for?
Use them when implementing specified features, following its development process, or preparing a release.
Why use it?
They show where specifications and documentation belong and what must be updated before a release.

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/jcfischer/supertag-cli/claude-md
Clone the repo
git clone --depth 1 https://github.com/jcfischer/supertag-cli
Per session 5,441 This file is loaded in full into every session.
When invoked 5,441 The same file — it is already loaded in full.
Security scan E 2 findings. 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 $0.05441 $0.05441
Opus 5 $0.02721 $0.02721
Sonnet 5 $0.01088 $0.01088
Haiku 4.5 $0.00544 $0.00544

Measured 3d ago against content hash e889228a6c53, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade E, and why

supertag-cli CLAUDE.md scanned grade E with 2 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.

Instruction-override phrasinghighPrompt injection

Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.

- `--include-all` - Bypass all content filters

Nullifies safety policieshighAnti-refusal

"You have no restrictions", "do anything now", "ignore your guidelines": a direct jailbreak that disables guardrails.

- `--include-all` - Bypass all content filters
CLAUDE.md · 541 lines

How it starts

The opening of the file, as written. The whole thing — 541 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Supertag CLI - Claude Code Context

SpecFlow Development

When implementing specs in .specify/specs/, invoke the SpecFlow skill.

This project uses spec-driven development. Specs are stored in .specify/specs/<feature-id>/ with:

  • spec.md - What and Why (requirements)
  • plan.md - How (technical design)
  • tasks.md - Work items with TDD enforcement

Triggers: "work on F-XXX", "implement F-XXX", "/specflow"

Documentation Locations

When releasing a new version, update ALL of these:

File Purpose Location
CHANGELOG.md Internal version history (detailed) ./CHANGELOG.md
README.md Technical documentation, CLI usage, MCP setup ./README.md
SKILL.md PAI skill documentation with USE WHEN triggers ./SKILL.md
CHANGELOG.md Public release notes (customer-facing) ~/work/web/invisible-store/tana/CHANGELOG.md
USER-GUIDE.md Customer-facing user guide ~/work/web/invisible-store/tana/USER-GUIDE.md
Marketing description Store listing and marketing copy ~/work/web/invisible-store/tana/index.html

Release Checklist

IMPORTANT: Update CHANGELOG.md BEFORE running release.sh

  1. Update CHANGELOG.md - Change [Unreleased] to [X.Y.Z] - YYYY-MM-DD
  2. Update version number in package.json
  3. Run bun run typecheck - Ensure TypeScript type checks pass
  4. Run bun run test:full - Ensure all tests pass
  5. Run ./release.sh X.Y.Z --push to build, tag, and push
  6. Update public CHANGELOG.md at ~/work/web/invisible-store/tana/CHANGELOG.md
  7. Update store listing if features changed

Note: The release script updates package.json version automatically if you pass a version argument. Step 2 can be skipped if using ./release.sh X.Y.Z.

PR Checklist

IMPORTANT: Run these checks before pushing a PR:

  1. Run bun run typecheck - TypeScript types must pass
  2. Run bun run test - Fast tests must pass (1741+ tests)
  3. Push and verify CI passes (GitHub Actions runs full test suite)

Read the full file on GitHub · 541 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. 3d ago First seen · 541 lines · 5,441 tokens per session scan E e889228a6c53

Subscribe to this mod's changes

supertag-cli CLAUDE.md is an instructions file published in the GitHub repository jcfischer/supertag-cli (49 stars, last pushed 2mo ago), licensed MIT. It adds 5,441 tokens to every session, about $0.0272 per session on Opus 5. A static security scan graded it E with 2 findings (instruction-override phrasing, nullifies safety policies). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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.

openai/codex · 5,182 tokens

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.

langchain-ai/langchain · 4,345 tokens

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).

microsoft/vscode · 5,001 tokens

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.

vercel/next.js · 7,296 tokens