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/thestreamcode/super-cli/agents-mdgit clone --depth 1 https://github.com/TheStreamCode/super-cliWhat 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 | $0.04078 | $0.04078 |
| Opus 5 | $0.02039 | $0.02039 |
| Sonnet 5 | $0.00816 | $0.00816 |
| Haiku 4.5 | $0.00408 | $0.00408 |
Grade A, and why
super-cli AGENTS.md scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
`doctor.ts` (Agent Doctor version checks via `node:child_process`, with an injectable runner for How it starts
The opening of the file, as written. The whole thing — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI coding agents (Claude Code, Codex, and others) working in this repository.
What this is
Super CLI is a VS Code extension (vscode-super-cli) that launches AI coding-agent CLIs (Claude
Code, Codex, Copilot CLI, and others) into native VS Code terminals from an activity-bar sidebar and
a quick-pick launcher. It has zero runtime dependencies — it only resolves and runs the shell
commands you configure; it never installs, wraps, or modifies a CLI or shell profile.
Commands
npm ci # install
npm run compile # tsc build: src/ -> out/
npm run typecheck # strict tsc check without emitting
npm run watch # tsc in watch mode
npm run test:unit # compile + fast unit tests (node:test against out/*.js)
npm run test:integration # compile + real VS Code Extension Development Host smoke test
npm run test # unit + integration
npm run audit # dependency advisories at moderate severity or higher
npm run check # compile + unit + integration + `vsce ls` packaging dry run
npm run package # build the .vsix via vsce
npm run check is what CI runs (.github/workflows/ci.yml, matrix over Windows/macOS/Linux) — run
it before submitting changes. There is no separate lint script; tsc --strict is the only static
check.
Before editing, inspect git status and the relevant files. Preserve unrelated local work, keep the
diff focused, and do not commit generated out/, .vscode-test/, .vsce/, coverage, log, .env, or
.vsix content. Do not bump the extension version unless the task is explicitly a release.
Unit tests require('../out/<name>.js'), so they run against compiled output, never src/
directly. To run a single test file, compile first, then point node --test at it:
npm run compile && node --test test/agents.test.js
The integration suite downloads/caches VS Code builds under .vscode-test/ (gitignored) via
@vscode/test-electron, launches a real Extension Development Host, and needs a display on Linux
(CI starts Xvfb for it).
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 · 270 lines · 4,078 tokens per session scan A 896810243dc3
super-cli AGENTS.md is an instructions file published in the GitHub repository TheStreamCode/super-cli (5 stars, last pushed 12d ago), licensed MIT. It adds 4,078 tokens to every session, about $0.0204 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
probity CLAUDE.md
Instructions for nizos/probity, covering probity, discipline and layout.
apm python.instructions.md
Python development guidelines.
amp-acp AGENTS.md
Instructions for tao12345666333/amp-acp, covering agents.md, commands, architecture and code style.
featherspec memory-bank.instructions.md
FeatherSpec Memory Bank writing rules (thin loader).
dev-workspace AGENTS.md
Instructions for iwe-org/dev-workspace, covering agent operating manual, start of every session, the operating loop, conventions and iwe basics.
loadout shell.instructions.md
Shell Script Engineering Instructions (Bash, CLI wrappers, automation).