Borrowing it
Nothing to install: this file belongs to procoders/superpowers-v. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/procoders/superpowers-v/main/AGENTS.mdgit clone --depth 1 https://github.com/procoders/superpowers-vWrote 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/procoders/superpowers-v/agents-md)<a href="https://agentmods.dev/instructions/procoders/superpowers-v/agents-md"><img src="https://agentmods.dev/badge/instructions/procoders/superpowers-v/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/procoders/superpowers-v/agents-md"><img src="https://agentmods.dev/badge/instructions/procoders/superpowers-v/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.06662 | $0.06662 |
| Opus 5.5 | $0.02665 | $0.02665 |
| Sonnet 5.5 | $0.01332 | $0.01332 |
| Haiku 4.5 | $0.00666 | $0.00666 |
Grade A, and why
superpowers-v AGENTS.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 8d 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compound V — Codex / Universal Agent Shim (🧪 experimental, untested)
This file documents how the plugin's content would be consumed by tools that read AGENTS.md from a project root (Codex CLI and similar). It has not been tested on a real Codex install — tool-name mappings and dispatch syntax are based on documentation and may need adaptation per your harness version.
Requirements
Claude Code ≥ 2.1.219. Compound V 3.0 hands execution to the native Workflow runtime and to native hook events (PreToolUse, UserPromptSubmit, PostCompact, Stop); older versions lack them. The SessionStart banner reads claude --version once and appends a single warning line when the running version is below that floor.
On measurement, stated up front. No speed or cost claim ships with 3.0. The observation that motivated proportionate tests — a small change running a full suite — was not reproduced during the design recon, so the test-scoping defaults are principle-derived, not measured. The scoped floor is early feedback and does not restore what a full suite guarantees; the merge-blocking CI run does, and it always runs. The pipeline records selected-test counts and measured-only durations so a future release can speak from real data instead.
One ambient cost worth knowing before you install. The lane-enforcement hook runs on every Write/Edit/Bash tool call in every session, and
its cost depends on the machine — it is a small table, not a single number — because it first has to find an interpreter that can read a manifest.
Measure it on your machine. This file publishes no figure: the repo carries no measurement harness to keep one honest, and every number it used to
print was a one-off on one laptop. The shape to expect: the unresolved path — the ordinary human session, and the only path a session that never
dispatches will ever take — is cheapest where the first candidate interpreter can import yaml (on macOS, /usr/bin/python3) and pays exactly one
viability probe, and dearest where no candidate has PyYAML and the hook pays three probes (two import yaml, one -c pass). Once a job
resolves and the manifest is parsed it costs more again, whether that write is then allowed or denied — the verdict has never been the expensive part;
resolution and the manifest parse are. What makes your own figure worth anything: mean of 50 invocations per cell, the bare-interpreter floor taken in
the same round and the round discarded when that floor drifts, and the unresolved path measured somewhere actually unresolved — a checkout that a live
run's lane map claims measures the resolved path and calls it unresolved. Reproduce it from a checkout root — the total divided by 50:
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.
- 8d ago Changed · +22 tokens per session 5a9bbeebb1c7
- 14d ago Changed · +233 tokens per session 87838796e25d
- 15d ago Changed · +5 lines · +416 tokens per session 5ea19ac79c50
- 20d ago Changed · +34 tokens per session da2c72473894
- 25d ago Changed · +1 lines · +104 tokens per session e6343fa510f3
- 26d ago Changed · +52 tokens per session 86e0cea1f13a
- 28d ago Changed · +6 lines · +394 tokens per session 8566fd287fbb
- 1mo ago Changed · +5 lines · +155 tokens per session d3f9eb3a67ad
- 1mo ago Changed · +24 lines · +640 tokens per session c02f0277f081
- 1mo ago First seen · 158 lines · 4,612 tokens per session scan A 041dcc81fe8e
superpowers-v AGENTS.md is an instructions file published in the GitHub repository procoders/superpowers-v (41 stars, last pushed 6d ago), licensed MIT. It adds 6,662 tokens to every session, about $0.0266 per session on Opus 5.5. 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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.