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/joshidikshant/devsquadWrote 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/joshidikshant/devsquad/plugin)<a href="https://agentmods.dev/plugins/joshidikshant/devsquad/plugin"><img src="https://agentmods.dev/badge/plugins/joshidikshant/devsquad/plugin/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/joshidikshant/devsquad/plugin"><img src="https://agentmods.dev/badge/plugins/joshidikshant/devsquad/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
devsquad 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 16d 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": "devsquad",
"version": "0.11.1",
"description": "Engineering Manager that coordinates AI coding agents through enforced delegation",
"author": {
"name": "Dikshant Joshi",
"url": "https://github.com/joshidikshant"
},
"repository": "https://github.com/joshidikshant/devsquad",
"homepage": "https://github.com/joshidikshant/devsquad#readme",
"license": "MIT",
"keywords": [
"delegation",
"orchestration",
"gemini",
"codex",
"multi-agent",
"token-management"
]
}
What it installs
The manifest is a name and a version. 8 skills, 8 commands, 8 agents, 4 hooks travel with it, and installing the plugin installs all of them — 1,826 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill environment-detection A 62 tokens
- Skill devsquad-config A 10 tokens
- Skill git-health A 34 tokens
- Skill devsquad-dispatch A 43 tokens
- Skill devsquad-status A 16 tokens
- Skill workflow-orchestration A 52 tokens
- Skill code-generation A 44 tokens
- Skill onboarding B 55 tokens
- Command capacity A 11 tokens
- Command models A 14 tokens
- Command config A 14 tokens
- Command generate A 21 tokens
- Command git-health A 28 tokens
- Command workflow A 32 tokens
- Command setup A 16 tokens
- Command status A 15 tokens
- Agent codex-tester A 220 tokens
- Agent codex-developer A 215 tokens
- Agent gemini-developer A 178 tokens
- Agent gemini-tester A 157 tokens
- Agent gemini-reader A 164 tokens
- Agent gemini-researcher A 162 tokens
- Agent grok-researcher A 139 tokens
- Agent grok-developer A 124 tokens
- Hook PreCompact A not measured
- Hook PreToolUse A not measured
- Hook SessionStart 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.
- 16d ago Changed · +1 lines ba1248ec7a94
- 1mo ago First seen · 20 lines scan A 5c0fdcb8a99e
devsquad is a plugin published in the GitHub repository joshidikshant/devsquad (7 stars, last pushed 17d 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
bounty-board
Turns your repo's tech debt into an aging bounty economy. A SessionStart hook scans tracked files and prices each TODO/FIXME/HACK/skip as a wanted-poster bounty whose XP grows with its git-blame age, injects the top 3 as opportunistic side quests, and, via a PostToolUse hook, verifies and pays out bounties that…
pr-provenance-stamp
Embeds a reviewer-facing provenance receipt into your PR body when Claude runs gh pr create (or glab mr create). A PostToolUse hook (async, zero added latency) records a per-session ledger: tool calls, agent-authored lines, and every test/typecheck command with its real exit code; a PreToolUse (Bash) hook then rewr.
claude-status-bar
Menu bar status indicator for Claude Code: animated spark, elapsed timer, and open/close lifecycle.
sipcode
Token-economy observatory for Claude Code: forensic per-session audit, A/B savings verifier, reproducible benchmark, and cost prediction — directly in Claude chat. Auto-installs via npx on first use; no separate npm install required.
phone-a-friend
Get second opinions, code reviews and multi-backend team feedback without leaving Claude Code, from Codex, Gemini, Antigravity, OpenCode, pi, Ollama or another Claude session. Requires the phone-a-friend CLI (Node.js 22.13+) and your own backend accounts or model servers; prompts and repository context go to the…
diffctx
Selects the minimum code an LLM needs to review a git diff.