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.
git clone --depth 1 https://github.com/edvardgrishin27/superstack-pluginWrote 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/plugins/edvardgrishin27/superstack-plugin/superstack)<a href="https://agentmods.dev/plugins/edvardgrishin27/superstack-plugin/superstack"><img src="https://agentmods.dev/badge/plugins/edvardgrishin27/superstack-plugin/superstack/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/plugins/edvardgrishin27/superstack-plugin/superstack"><img src="https://agentmods.dev/badge/plugins/edvardgrishin27/superstack-plugin/superstack.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
superstack 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 1mo 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.
What it actually says
{
"name": "superstack",
"version": "0.13.0",
"description": "Агентная система разработки: ведёт от фразы до доказанного куска через блокирующие гейты на плане и верификации, объясняет каждый вывод человеческим языком и доказывает работоспособность живым прогоном.",
"author": {
"name": "Edvard Grishin"
},
"license": "MIT",
"keywords": [
"claude-code",
"audit",
"gates",
"security"
],
"skills": [
"./skills/"
],
"agents": [
"./agents/blind-acceptance.md",
"./agents/builder.md",
"./agents/second-opinion.md"
]
}
What it installs
The manifest is a name and a version. 7 skills, 3 agents, 3 hooks travel with it, and installing the plugin installs all of them — 313 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill oops A 125 tokens
- Skill change A 0 tokens
- Skill stop A 0 tokens
- Skill fix A 0 tokens
- Skill what A 101 tokens
- Skill go A 0 tokens
- Skill superstack D 0 tokens
- Agent blind-acceptance A 0 tokens
- Agent builder A 87 tokens
- Agent second-opinion A 0 tokens
- Hook SessionStart A not measured
- Hook PreCompact A not measured
- Hook Stop A not measured
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.
- 1mo ago Changed 7cd1939fb8e8
- 1mo ago Changed 2ac01af6f816
- 1mo ago Changed 6616faa75d65
- 1mo ago First seen · 24 lines scan A 18228a74a006
superstack is a plugin published in the GitHub repository edvardgrishin27/superstack-plugin (17 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
arrow-maintenance
Scaling layer for linked-intent-dev. Tracks spec-to-code coherence across large projects via docs/arrows/ index. Includes brownfield bootstrap for mapping existing codebases.
lid-experimental
Experimental LID skills with opt-in installation and explicit lifecycle (promotion or retirement). Layers on top of linked-intent-dev and arrow-maintenance.
linked-intent-dev
Structured design-before-code workflow: HLD → LLD → EARS specs → Tests → Code.
polygraph
A polygraph for your state machine. The agent does the hard part for you: it instruments your code, builds any test doubles needed to run it, and captures real execution traces — then has an LLM derive a transition-function spec from the source (default: a SAM v2 strict-profile module with named…
agent-work-protocol
An always-on operating protocol for coding agents: build only what's asked, surface ambiguity as Q/A/P/E/X, scale process to task size, and verify before claiming. Injected into every session via a SessionStart hook.
game-qa
Verify browser-based game features through a PM-driven QA loop. Ships a project-agnostic runner + adapter skeleton + journey schema so projects onboard by copy-and-adapt, not natural-language reconstruction. Six skills covering request → plan → execute → review → rollup, plus the bootstrap that drops the framework…