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/jpd44/mesh44-plugins/asknpx skills add jpd44/mesh44-plugins --skill askgit clone --depth 1 https://github.com/jpd44/mesh44-pluginsWhat 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 | $0.00042 | $0.00476 |
| Opus 5 | $0.00021 | $0.00238 |
| Sonnet 5 | $0.00008 | $0.00095 |
| Haiku 4.5 | $0.00004 | $0.00048 |
Grade A, and why
ask 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 yesterday.
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
/cost:ask — natural-language AWS cost questions
Answer questions like "why did spend jump in June?", "which app grew the most this quarter?", or "what's my biggest service across every app?" using the user's local cost data. Keep it local-first — work from the on-disk snapshot; don't ship their figures anywhere.
Get the data
Use the mesh44-cost tool's local snapshot (jpd44/mesh44-cost, typically ~/Developer/mesh44-cost/public/data.json).
- If
public/data.jsonis missing or stale (check itsgeneratedAt), refresh it:
Runcd ~/Developer/mesh44-cost && AWS_PROFILE=mgt npm run fetchaws sso login --profile mgtfirst if the SSO session is expired. - Read
public/data.json. It contains:months,totalsByMonth,totalThisMonth,totalLastMonth,forecastThisMonthapps[]— per account:name,accountId,series(6-month),current,previous,topServicetopServices[]— service + amount for the current month
Answer
- Compute the specifics from the JSON: deltas, % change, which account/service drove a change, trend direction, forecast vs. last month.
- Cite concrete numbers — e.g. "June was $58.40, up 42% from May's $41.00, driven by daily-deutsch's load balancer ($44 of it)."
- If the question needs a dimension the snapshot doesn't have (daily granularity, a specific tag, a service within one account over time), say so and offer to pull it with a targeted Cost Explorer query via the AWS CLI (
aws ce get-cost-and-usage ... --profile mgt).
Privacy contract
Read-only, local-first. The data stays on the user's machine; use only the figures needed to answer.
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.
- yesterday First seen · 32 lines · 42 tokens per session scan A 45a5cb8c64a5
ask is a skill published in the GitHub repository jpd44/mesh44-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 476 once invoked, about $0.0002 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.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…