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 cyberelf/agent_skills --skill insight-knowledge-harvestgit clone --depth 1 https://github.com/cyberelf/agent_skillsWrote 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/cyberelf/agent_skills/insight-knowledge-harvest)<a href="https://agentmods.dev/skills/cyberelf/agent_skills/insight-knowledge-harvest"><img src="https://agentmods.dev/badge/skills/cyberelf/agent_skills/insight-knowledge-harvest/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/cyberelf/agent_skills/insight-knowledge-harvest"><img src="https://agentmods.dev/badge/skills/cyberelf/agent_skills/insight-knowledge-harvest.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 | $0.00085 | $0.05946 |
| Opus 5 | $0.00043 | $0.02973 |
| Sonnet 5 | $0.00017 | $0.01189 |
| Haiku 4.5 | $0.00009 | $0.00595 |
Grade A, and why
insight-knowledge-harvest 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 — 348 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Insight Knowledge Harvest
Use this skill to build and incrementally expand a curated raw-material layer for future viewpoint and insight extraction.
This is a source-ingestion and verification workflow, not a final insight-writing workflow. Its job is to inspect the current KB as context, promote or discover candidate page-level sources, deduplicate them, capture accepted pages into raw Markdown, and keep ingest plus verification state aligned across the project.
The operating model is intentionally simple:
source/raw/stores one raw page capture per canonical source page or document, plus minimal identity, processing-state, and high-level classification metadata.source/ingest.mdtracks minimal pipeline state for every candidate or accepted material.source/registers/holds curator-facing notes such as rejection reasons, gap lists, deep-read queues, and the classification schema vocabulary.source/.harvest/optionally stores hidden operational deduplication state and detailed classification metadata in SQLite for broader discovery runs.
In default additive mode, existing materials are treated as read-only context for topic promotion, deduplication, and gap detection. The skill normally adds new page-level captures, verifies newly downloaded files in place, and avoids rewriting prior raw materials unless the user explicitly asks for repair or re-verification.
Raw files must remain raw captures, not summaries. Curator judgment belongs in ingest, register notes, or the internal SQLite index, while the raw file keeps only source identity, processing-state metadata, and the high-level classification trio: material_kind, topic_domain, and credibility_tier.
At a glance, this skill is best when you need to:
- grow an evidence base before insight extraction,
- keep one-file-per-page provenance clean,
- run incremental source discovery without reprocessing the whole archive,
- and preserve a separation between raw source content and curator-written interpretation.
What ships with it
7 files 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.
- agents/source-material-downloader.agent.md 6.4 KB
- agents/source-material-verifier.agent.md 5.1 KB
- assets/ingest-list-template.md 2.2 KB
- assets/source-material-template.md 3.6 KB
- references/classification-schema.md 8.8 KB
- references/source-priority.md 5.9 KB
- scripts/precrawl_link_index.py 36 KB runs code
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 · 348 lines · 85 tokens per session scan A 55b2588d0be4
insight-knowledge-harvest is a skill published in the GitHub repository cyberelf/agent_skills (2 stars, last pushed 15d ago), licensed MIT. It adds 85 tokens to every session and 5,946 once invoked, about $0.0004 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…