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/automateyournetwork/netclawWrote 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/commands/automateyournetwork/netclaw/speckit.analyze)<a href="https://agentmods.dev/commands/automateyournetwork/netclaw/speckit.analyze"><img src="https://agentmods.dev/badge/commands/automateyournetwork/netclaw/speckit.analyze/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/commands/automateyournetwork/netclaw/speckit.analyze"><img src="https://agentmods.dev/badge/commands/automateyournetwork/netclaw/speckit.analyze.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 | $0.00009 | $0.00277 |
| Opus 5.5 | $0.00004 | $0.00111 |
| Sonnet 5.5 | $0.00002 | $0.00055 |
| Haiku 4.5 | $0.00001 | $0.00028 |
Grade C, and why
speckit.analyze scanned grade C with 1 finding 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 13d 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
This is a deployment workspace, not the NetClaw development repository. Read the shared netclaw-install skill. Use only the provisioning MCP tools. No command in this workflow authorizes executing scripts/install.sh, ano What it actually says
Analyze a NetClaw deployment
NETCLAW_DEPLOYMENT_PRESET_153_V1
This is a deployment workspace, not the NetClaw development repository. Read the shared netclaw-install skill. Use only the provisioning MCP tools. No command in this workflow authorizes executing scripts/install.sh, another installer, an arbitrary command, apply, resume or cleanup. Never collect secrets in chat or files. Native secret entry returns presence only. Existing installations are preserved; new homes are independent.
Use deployment-spec.md, netclaw-plan.json, deployment-tasks.md, analysis.md and the default redacted claw-report.json. Required choices remain explicit; assumptions and unresolved decisions block apply. Source and host are reviewed in native setup. Production stays blocked when mandatory controls are unsupported or unverified. Do not substitute requested settings for observed enforcement. Every runtime/verification claim must identify actual evidence and limits.
Read deployment-spec.md, netclaw-plan.json and deployment-tasks.md. Validate the canonical draft and inspect explanation. Check missing/contradictory choices, paths/ports/service collisions, supported profiles, independent secret ownership, production control evidence and every verification requirement. Write analysis.md with findings; resolve all findings before review. Never declare readiness from prose alone.
User input: $ARGUMENTS
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.
- 13d ago First seen · 16 lines · 9 tokens per session scan C daee53c802cd
speckit.analyze is a command published in the GitHub repository automateyournetwork/netclaw (715 stars, last pushed yesterday), licensed Apache-2.0. It adds 9 tokens to every session and 277 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it C with 1 finding (harvests environment variables). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-25.
speckit.analyze compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| speckit.analyzeautomateyournetwork/netclaw | Command | 715 | yesterday | Apache-2.0 | C | 9 | Claude Code |
| statusluongnv89/claude-howto | Command | 47k | 3d ago | MIT | A | 6 | Claude Code |
| investigateaws/agent-toolkit-for-aws | Command | 3.4k | yesterday | Apache-2.0 | A | 16 | Claude Code |
| cloudflare-workers:debugsecondsky/claude-skills | Command | 245 | 6d ago | MIT | A | 31 | Claude Code |
| cloudflare-queues:troubleshootsecondsky/claude-skills | Command | 245 | 6d ago | MIT | A | 18 | Claude Code |
| cloudflare-workflows:debugsecondsky/claude-skills | Command | 245 | 6d ago | MIT | A | 28 | Claude Code |
| cloud-run-debugyuting0624/antigravity-for-claude-code | Command | 473 | 4d ago | MIT | A | 49 | Claude Code |