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 skills/thanhtung2693/specgate/specgate-project-setupnpx skills add thanhtung2693/specgate --skill specgate-project-setupgit clone --depth 1 https://github.com/thanhtung2693/specgateWrote 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/thanhtung2693/specgate/specgate-project-setup)<a href="https://agentmods.dev/skills/thanhtung2693/specgate/specgate-project-setup"><img src="https://agentmods.dev/badge/skills/thanhtung2693/specgate/specgate-project-setup.svg" alt="Measured on agentmods" 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 | $0.00037 | $0.01028 |
| Opus 5 | $0.00018 | $0.00514 |
| Sonnet 5 | $0.00007 | $0.00206 |
| Haiku 4.5 | $0.00004 | $0.00103 |
Grade C, and why
specgate-project-setup 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 5d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://raw.githubusercontent.com/thanhtung2693/specgate/main/scripts/install-cli.sh | sh Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://raw.githubusercontent.com/thanhtung2693/specgate/main/scripts/install-cli.sh | sh How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setting Up SpecGate
Apply the SpecGate operating contract. This phase configures SpecGate; it does not create specifications or product work.
1. Ensure the CLI is available
Use the host shell's command lookup before running any SpecGate command:
command -v specgate
Get-Command specgate -ErrorAction SilentlyContinue
When lookup succeeds, run specgate --version and continue to inspect the
current state.
Installing from skills.sh does not install the SpecGate CLI; it provides agent instructions only. If the command is missing on macOS, Linux, or WSL2, show the user the exact installer command and wait for explicit approval before running it:
curl -fsSL https://raw.githubusercontent.com/thanhtung2693/specgate/main/scripts/install-cli.sh | sh
A general request to set up or initialize SpecGate is not approval to download
and execute the installer. On native Windows, offer WSL2 with the command above
or direct the user to
https://github.com/thanhtung2693/specgate/releases/latest; do not invent a
PowerShell installer. After installation, run specgate --version. If lookup
still fails, report the install path and PATH recovery printed by the installer.
Completion criterion: the installed CLI version is recorded, or setup is paused for explicit installer approval or native Windows installation.
2. Inspect the current state
specgate doctor --json
Use the doctor's reported state and recovery action. In an existing topology, follow that recovery action instead of rerunning initialization or switching mode. Initialization is required only when doctor reports no initialized topology.
Completion criterion: every failing doctor check is recorded, or doctor confirms the current topology is healthy.
3. Initialize only when required
The user chooses Local or Full mode; never infer that product decision from Docker, a URL, or installed software. In an interactive terminal, run exactly the chosen mode:
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.
- 5d ago First seen · 141 lines · 37 tokens per session scan C 31ee94e17bbe
specgate-project-setup is a skill published in the GitHub repository thanhtung2693/specgate (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 37 tokens to every session and 1,028 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
weave
Parallel strand orchestration — decompose a task into 3+ independently scoped strands, fan out real subagents (worktree-isolated when they write files), and coordinate through a session file and Insight Capsules. Use ONLY when the user explicitly invokes it by name or slash command.
coding-agents-farm
To orchestrate parallel coding-agent farms (Claude, Codex, Copilot, Gemini, etc.) on isolated git worktrees.
mcp-media-inbox-triage
Find media, partnership, and high-intent requests buried in a shared Gmail inbox, summarize the useful ones, and route them to the right owner through Zapier MCP.
customer-deck-builder
Build tailored customer-facing sales or customer success decks from approved account context and generate the presentation with Gamma through Zapier MCP.
premortem
First-principles premortem on a high-stakes plan: assume failure 6–18 months out, reconstruct causal death chains, surface hidden assumptions, deliver a revised reversibility-weighted plan. Use ONLY when the user explicitly invokes it by name or slash command.
bcc-plan-spar
BCC align+lock+review PLAN.md for one slice (no product code). Slash: /bcc-plan-spar · chat: bcc:plan-spar · "lock PLAN" · spar the plan. Args: rounds=N (auto-review cap), review=self|subagent|cli|auto|off. Grill until clear enough (no default Q&A quota). Hand off to bcc-clean-cut after human APPROVE.