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 AIOProductOS/claude-plugin --skill aioproductos-triagegit clone --depth 1 https://github.com/AIOProductOS/claude-pluginWrote 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/aioproductos/claude-plugin/aioproductos-triage)<a href="https://agentmods.dev/skills/aioproductos/claude-plugin/aioproductos-triage"><img src="https://agentmods.dev/badge/skills/aioproductos/claude-plugin/aioproductos-triage/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/aioproductos/claude-plugin/aioproductos-triage"><img src="https://agentmods.dev/badge/skills/aioproductos/claude-plugin/aioproductos-triage.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 | $0.00098 | $0.01519 |
| Opus 5 | $0.00049 | $0.00759 |
| Sonnet 5 | $0.00020 | $0.00304 |
| Haiku 4.5 | $0.00010 | $0.00152 |
Grade A, and why
aioproductos-triage 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 9d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AIOProductOS · Weekly Triage
Turn a week's customer signal into 3 scheduled, owned, evidence-backed tasks — in one pass over the AIOProductOS spine. Insight → feature → task → sprint, with the revenue and usage that justify each call carried on the same record.
Before you start
This skill drives the AIOProductOS MCP connector. It needs these tools to be
available in the session: get_pm_playbook, get_product_brain, list_insights,
get_customer_360, list_objectives, pm_meta, create_task, update_task,
list_sprints (plus the analytics reads analyze_nrr, analyze_funnel,
get_retention, analyze_paths).
If those tools are not present, stop and tell the user to connect the workspace:
Settings → Connect & Tokens → "Connect to Claude", custom connector URL
https://platform.aioproductos.com/api/mcp. Don't fabricate the triage — without
the connector there is no spine to ground in.
The doctrine (load it, don't guess it)
Call get_pm_playbook once and follow it. The non-negotiables it encodes:
- Ground in the brain, then decide. Never reason about priorities from memory.
- Keep work on the spine. Every task links its
insight_id(the why) and itsfeature_id(the bet). No orphans. - Resolve names → ids with
pm_metabefore any write. Never guess an id. - Claim only the writes you actually made, in plain language.
The flow
1 · Ground
Call get_product_brain — revenue + top accounts, web + product analytics,
features, recent verbatim signals, open work. This is your whole evidence base for
the session. Pull list_objectives too, so every bet you propose ties to a goal
the team is actually trying to move.
2 · Surface candidates
Call list_insights (open, newest first) — the voice-of-customer backlog. Combine
with the recent signals from the brain. Cluster duplicates: three accounts asking
for SSO is one opportunity with reach 3, not three items.
3 · Weigh on real evidence → pick the top 3
For the strongest candidates, quantify the case from the spine, never from a hunch:
- Revenue at stake —
get_customer_360on the accounts each item touches (MRR behind them);analyze_nrrfor what's churning or contracting. - Reach / usage —
analyze_funnel,get_retention,analyze_paths, or the brain's analytics: how many users actually hit this. - Signal strength — how many distinct accounts, how recent, quantitative vs. anecdotal.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 117 lines · 98 tokens per session scan A 3052782a3e3d
aioproductos-triage is a skill published in the GitHub repository AIOProductOS/claude-plugin (0 stars, last pushed 1mo ago), licensed MIT. It adds 98 tokens to every session and 1,519 once invoked, about $0.0005 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…
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…