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 aavaz-ai/enterpret-claude-plugins --skill evidence-synthesisgit clone --depth 1 https://github.com/aavaz-ai/enterpret-claude-pluginsWrote 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/aavaz-ai/enterpret-claude-plugins/evidence-synthesis)<a href="https://agentmods.dev/skills/aavaz-ai/enterpret-claude-plugins/evidence-synthesis"><img src="https://agentmods.dev/badge/skills/aavaz-ai/enterpret-claude-plugins/evidence-synthesis/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/aavaz-ai/enterpret-claude-plugins/evidence-synthesis"><img src="https://agentmods.dev/badge/skills/aavaz-ai/enterpret-claude-plugins/evidence-synthesis.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 | $0.00057 | $0.01874 |
| Opus 5 | $0.00028 | $0.00937 |
| Sonnet 5 | $0.00011 | $0.00375 |
| Haiku 4.5 | $0.00006 | $0.00187 |
Grade A, and why
evidence-synthesis 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 10d 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Customer Evidence Synthesis
This skill governs how you turn raw KG query results into evidence that PMs, executives, and engineers can act on. The output should feel like analysis from a skilled researcher, not a database export.
Core Principle
Synthesize, never dump. The value you provide is narrative and interpretation, not raw retrieval. Anyone can pull numbers — what PMs need is someone to tell them what the numbers mean, why they matter now, and what to do about it.
Quote Selection Rules
CRITICAL: Use actual customer words, not AI summaries
Quotes MUST come from nli.content (the customer's verbatim words), NOT fi.content (the AI-generated summary). If a query returns fi.content, it is a summary — do not present it as a customer quote. Always query nli.content AS verbatim for customer-facing quotes.
CRITICAL: Every quote must have a date
Every quote MUST include its nli.record_timestamp as a date. A quote without a date has no temporal context — the reader can't tell if it's from yesterday or 2 weeks ago. Never omit the date.
How many: 3-5 maximum per section
More than 5 quotes becomes a data dump. Fewer than 3 feels cherry-picked. The sweet spot is 3-5 carefully chosen quotes that together tell a complete story. For top themes in reports, aim for 3+ quotes minimum.
Diversity requirements:
- Different subthemes — don't pick 3 quotes about the same narrow issue
- Different time periods — show the problem exists across time, not just one spike
- Different sentiment angles — if possible, include one that shows the severity (frustrated) and one that shows the impact (workaround, churn mention)
- Recency bias toward recent — lead with the most recent quote, but include at least one older quote to show persistence
Selection criteria (prefer quotes that):
- Illustrate with specific detail — "The CSV import fails every time I have more than 500 rows" > "Import doesn't work"
- Show business impact — "We had to manually re-enter 200 records" > "This is annoying"
- Represent the majority pattern — don't lead with an outlier
- Include context — quotes with timestamps, account info, or channel context are more credible
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.
- 10d ago First seen · 149 lines · 57 tokens per session scan A ca3c9e759cda
evidence-synthesis is a skill published in the GitHub repository aavaz-ai/enterpret-claude-plugins (2 stars, last pushed 5mo ago), licensed MIT. It adds 57 tokens to every session and 1,874 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…
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…