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 juicesharp/rpiv-mono --skill synthesizegit clone --depth 1 https://github.com/juicesharp/rpiv-monoWrote 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/juicesharp/rpiv-mono/synthesize)<a href="https://agentmods.dev/skills/juicesharp/rpiv-mono/synthesize"><img src="https://agentmods.dev/badge/skills/juicesharp/rpiv-mono/synthesize/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/juicesharp/rpiv-mono/synthesize"><img src="https://agentmods.dev/badge/skills/juicesharp/rpiv-mono/synthesize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
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 →
- medium MCP Rug Pull · line 171 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Excessive Agency · line 105 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.
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 | $0.00162 | $0.03643 |
| Opus 5 | $0.00081 | $0.01821 |
| Sonnet 5 | $0.00032 | $0.00729 |
| Haiku 4.5 | $0.00016 | $0.00364 |
Grade A, and why
synthesize 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 7d 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Synthesize
You merge several independent per-slice designs into one coherent phased plan. One pass. You do not redesign a slice or write code — you reconcile and sequence what the slice designs already decided. This is the fan-in barrier: each design was produced blind to the others, so your job is to make them fit together. No subagents, no self-review — the workflow's grade panel judges the merged plan.
Input
$ARGUMENTS — flags (the orchestrator wires them from the fan-in):
--designs <path>(repeats) — per-slice design docs from the design fanout.--subplans <path>(repeats) — partial sub-plans from a cluster fanout (root mode).--research <path>(optional) — the research the slices rest on, for cross-slice constraints.--as-subplan(flag) — emit a sub-plan (partial mode) instead of a full plan.--cluster <k>(optional, partial mode) — the ordinal written into the sub-plan's_cluster-<k>.mdfilename. The cluster fanout supplies it; for manual partial invocation pick an unused<k>(scan.rpiv/artifacts/subplans/for existing*_cluster-<k>.mdand take the next unused positive integer) so a re-dispatched pass writes a distinct file and never clobbers a sibling sub-plan.
If neither --designs nor --subplans is present, print an error and stop.
Modes
Pick the mode from the flags — the work is the same fan-in reconciliation at three scales:
| Mode | Selected by | Reads | Writes to | Output kind |
|---|---|---|---|---|
| Flat (default) | --designs only |
every design | .rpiv/artifacts/plans/ |
full plan |
| Partial (per-cluster) | --designs … --as-subplan |
one cluster's designs | .rpiv/artifacts/subplans/ |
sub-plan |
| Root (merge) | --subplans … |
the cluster sub-plans | .rpiv/artifacts/plans/ |
full plan |
Hierarchical synthesis (partial → root) bounds each pass's context: a partial sees only its cluster's designs and exports the seams other clusters integrate with; the root merges the compact sub-plans (their summary + exports + phases), never re-reading every design. Flat mode is the single-pass form for small slice maps.
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.
- 7d ago Changed 0ffdfada5ecc
- 11d ago First seen · 176 lines · 162 tokens per session scan A 8c89c63d8636
synthesize is a skill published in the GitHub repository juicesharp/rpiv-mono (779 stars, last pushed today), licensed MIT. It adds 162 tokens to every session and 3,643 once invoked, about $0.0008 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 2026-08-30.
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…
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…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…