gstack is a set of opinionated tools that gives a coding agent workflows associated with roles such as product leadership, design, engineering management, release management, documentation, and quality assurance. It is for developers who want one coding agent to support more parts of the software delivery process.
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 skills add garrytan/gstack --skill gstack-upgradegit clone --depth 1 https://github.com/garrytan/gstackWrote 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/skills/garrytan/gstack/gstack-upgrade)<a href="https://agentmods.dev/skills/garrytan/gstack/gstack-upgrade"><img src="https://agentmods.dev/badge/skills/garrytan/gstack/gstack-upgrade/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/skills/garrytan/gstack/gstack-upgrade"><img src="https://agentmods.dev/badge/skills/garrytan/gstack/gstack-upgrade.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 12 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 147 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 165 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 272 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 179 Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.Fix: Limit tool chaining depth and validate the output of each tool before passing it to the next. Require explicit user approval for multi-step chains.
- high Agent Snooping · line 216 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high Tool Misuse · line 227 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 318 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 319 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Excessive Agency · line 154 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Rogue Agent · line 12 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 59 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 313 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00013 | $0.06266 |
| Opus 5.5 | $0.00005 | $0.02506 |
| Sonnet 5.5 | $0.00003 | $0.01253 |
| Haiku 4.5 | $0.00001 | $0.00627 |
Grade C, and why
gstack-upgrade scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
git clone --depth 1 https://github.com/garrytan/gstack.git "$TMP_DIR/gstack" || { echo "ERROR: clone failed — aborting upgrade (install untouched)." >&2; rm -rf "$TMP_DIR"; exit 1; } Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
elif curl -fsS --max-time 2 "http://127.0.0.1:$DAEMON_PORT/health" 2>/dev/null | grep -q '"status":"healthy"'; then Copies of this mod
6 near-identical copies found in the catalogue:
- gstack-upgrade — 91% identical, 227 lines differ
- gstack-upgrade — 89% identical, 281 lines differ
- gs:gstack-upgrade — 88% identical, 304 lines differ
- gstack-upgrade — 86% identical, 270 lines differ
- gstack-upgrade — 86% identical, 273 lines differ
- gstack-upgrade — 77% identical, 313 lines differ
How it starts
The opening of the file, as written. The whole thing — 417 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to invoke this skill
Detects global vs vendored install, runs the upgrade, and shows what's new. Use when asked to "upgrade gstack", "update gstack", or "get latest version".
Voice triggers (speech-to-text aliases): "upgrade the tools", "update the tools", "gee stack upgrade", "g stack upgrade".
/gstack-upgrade
Upgrade gstack to the latest version and show what's new.
Inline upgrade flow
This section is referenced by all skill preambles when they detect UPGRADE_AVAILABLE.
Step 1: Ask the user (or auto-upgrade)
First, check if auto-upgrade is enabled:
_AUTO=""
[ "${GSTACK_AUTO_UPGRADE:-}" = "1" ] && _AUTO="true"
[ -z "$_AUTO" ] && _AUTO=$(~/.claude/skills/gstack/bin/gstack-config get auto_upgrade 2>/dev/null || true)
echo "AUTO_UPGRADE=$_AUTO"
If AUTO_UPGRADE=true or AUTO_UPGRADE=1: Skip AskUserQuestion. Log "Auto-upgrading gstack v{old} → v{new}..." and proceed directly to Step 2. On setup failure, follow Step 4's install-specific recovery: vendored installs restore their backup; git installs stop with the pre-upgrade commit recorded, without a destructive reset. Never claim restoration unless it actually succeeded.
Otherwise, use AskUserQuestion:
- Question: "gstack v{new} is available (you're on v{old}). Upgrade now?"
- Options: ["Yes, upgrade now", "Always keep me up to date", "Not now", "Never ask again"]
If "Yes, upgrade now": Proceed to Step 2.
If "Always keep me up to date":
~/.claude/skills/gstack/bin/gstack-config set auto_upgrade true
Tell user: "Auto-upgrade enabled. Future updates will install automatically." Then proceed to Step 2.
If "Not now": Write snooze state with escalating backoff (first snooze = 24h, second = 48h, third+ = 1 week), then continue with the current skill. Do not mention the upgrade again.
GSTACK_STATE_ROOT=$(~/.claude/skills/gstack/bin/gstack-paths --get GSTACK_STATE_ROOT); : "${GSTACK_STATE_ROOT:?gstack-paths failed; reinstall with ./setup or /gstack-upgrade}"
_SNOOZE_FILE="$GSTACK_STATE_ROOT/update-snoozed"
_REMOTE_VER="{new}"
_CUR_LEVEL=0
if [ -f "$_SNOOZE_FILE" ]; then
_SNOOZED_VER=$(awk '{print $(1)}' "$_SNOOZE_FILE")
if [ "$_SNOOZED_VER" = "$_REMOTE_VER" ]; then
_CUR_LEVEL=$(awk '{print $(2)}' "$_SNOOZE_FILE")
case "$_CUR_LEVEL" in *[!0-9]*) _CUR_LEVEL=0 ;; esac
fi
fi
_NEW_LEVEL=$((_CUR_LEVEL + 1))
[ "$_NEW_LEVEL" -gt 3 ] && _NEW_LEVEL=3
echo "$_REMOTE_VER $_NEW_LEVEL $(date +%s)" > "$_SNOOZE_FILE"
Note: {new} is the remote version from the UPGRADE_AVAILABLE output — substitute it from the update check result.
What ships with it
17 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- migrations/v0.15.2.0.sh 854 B runs code
- migrations/v0.16.2.0.sh 2.7 KB runs code
- migrations/v1.0.0.0.sh 2.0 KB runs code
- migrations/v1.1.3.0.sh 5.9 KB runs code
- migrations/v1.17.0.0.sh 2.5 KB runs code
- migrations/v1.27.0.0.sh 19 KB runs code
- migrations/v1.37.0.0.sh 4.6 KB runs code
- migrations/v1.38.1.0.sh 4.0 KB runs code
- migrations/v1.40.0.0.sh 5.8 KB runs code
- migrations/v1.58.0.0.sh 2.8 KB runs code
- migrations/v1.65.0.0.sh 7.6 KB runs code
- migrations/v1.67.0.0.sh 2.8 KB runs code
- migrations/v1.78.0.0.sh 1.5 KB runs code
- migrations/v1.86.0.0.sh 685 B runs code
- migrations/v1.91.19.0.sh 3.3 KB runs code
- migrations/v1.91.65.0.sh 1.9 KB runs code
- SKILL.md.tmpl 22 KB
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.
- 4d ago Changed 48e54249ee61
- 9d ago Changed · +3 lines 10519b684f50
- 11d ago Changed · +12 lines 79f790d98a91
- 12d ago Changed · +6 lines 24d9c2b2bb65
- 13d ago Changed · +4 lines fa7d7128e23d
- 14d ago Changed · +2 lines e0afdf77c6f3
- 19d ago Changed 4c4b9265aef4
- 1mo ago Changed · +15 lines 7991b58152ac
- 1mo ago Changed · +11 lines 60e5015f7eab
- 1mo ago First seen · 364 lines · 13 tokens per session scan C 14248eed79a3
gstack-upgrade is a skill published in the GitHub repository garrytan/gstack (136,569 stars, last pushed today), licensed MIT. It adds 13 tokens to every session and 6,266 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…