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/datatorag/mcp-gateway/parent-updatesnpx skills add datatorag/mcp-gateway --skill parent-updatesgit clone --depth 1 https://github.com/datatorag/mcp-gatewayWrote 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/datatorag/mcp-gateway/parent-updates)<a href="https://agentmods.dev/skills/datatorag/mcp-gateway/parent-updates"><img src="https://agentmods.dev/badge/skills/datatorag/mcp-gateway/parent-updates.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 | $0.00063 | $0.01032 |
| Opus 5 | $0.00032 | $0.00516 |
| Sonnet 5 | $0.00013 | $0.00206 |
| Haiku 4.5 | $0.00006 | $0.00103 |
Grade A, and why
parent-updates 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parent Updates
This session runs as an AgentDeck child of datatorag-hq. HQ writes the
briefs and owns the decisions, but it cannot see anything in this session —
not the tool calls, not the test output, not the thing you just discovered
that invalidates its brief. The only channel is an explicit send.
agent-deck session send datatorag-hq "..."
SendMessage does not reach it. It has to be this command.
When to send
Send at these moments, not on a timer:
- Work lands. A build finishes, a gate passes, a push goes out, a deploy completes. Include what was verified and how, not just that it is done.
- A decision is needed. Anything where proceeding either way is defensible and the choice is HQ's. Send the options and a recommendation, then keep building whatever does not depend on the answer.
- A blocker appears. Say what is blocked, what it is blocked on, and whose action unblocks it.
- A brief's premise turns out to be wrong. This is the highest-value send and the easiest to skip. If HQ says a tenant is suspended and it is not, or hedges on something that is not a maybe, correcting it early is worth more than the work you were asked to do.
- Something durable is learned. A defect, an API constraint, a false-negative trap. HQ stores these; this session's context does not survive.
Do NOT send a running commentary. A send that says "starting on X" costs HQ attention and tells it nothing it cannot infer.
What a good send contains
- The verdict first. Done, blocked, or needs a decision.
- What was verified, and how. "327 tests passing, cache-busted with cf-cache-status DYNAMIC" beats "verified". HQ is deciding whether to trust the result; give it the basis.
- Corrections, plainly. If you were wrong earlier, or HQ was, say which and what the right answer is. Do not bury it.
- What is still outstanding, so HQ can sequence the next brief.
- Cleanup owed by a human — a test ticket that cannot be deleted by tool, a throwaway file, a console action.
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 · 93 lines · 63 tokens per session scan A 9c04ef4f57ba
parent-updates is a skill published in the GitHub repository datatorag/mcp-gateway (3 stars, last pushed today), licensed MIT. It adds 63 tokens to every session and 1,032 once invoked, about $0.0003 per session on Opus 5. 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…