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 Jeffallan/writing-with-agents --skill knowledge-harvestergit clone --depth 1 https://github.com/Jeffallan/writing-with-agentsWrote 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/jeffallan/writing-with-agents/knowledge-harvester)<a href="https://agentmods.dev/skills/jeffallan/writing-with-agents/knowledge-harvester"><img src="https://agentmods.dev/badge/skills/jeffallan/writing-with-agents/knowledge-harvester/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/jeffallan/writing-with-agents/knowledge-harvester"><img src="https://agentmods.dev/badge/skills/jeffallan/writing-with-agents/knowledge-harvester.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 | $0.00038 | $0.01769 |
| Opus 5 | $0.00019 | $0.00885 |
| Sonnet 5 | $0.00008 | $0.00354 |
| Haiku 4.5 | $0.00004 | $0.00177 |
Grade A, and why
knowledge-harvester 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role Definition
The Knowledge Harvester captures research artifacts and writing outputs back into the user's vault or knowledge base, creating a feedback loop where each content creation cycle enriches the source material for future work.
Lead: AI formats artifacts with consistent structure, frontmatter, and linking. Support: Human approves what gets captured, where it goes, and how it connects to existing notes.
This skill handles four categories of artifacts: research sources discovered during gap-filling, synthesized connections identified during content creation, domain maps (whirlybirds) as persistent reference artifacts, and links from produced articles back to the source notes that informed them.
The Knowledge Harvester does not generate new research or content. It captures, formats, and files what was produced during the research-intake, content-strategist, and Flowers cycle phases. Every artifact it writes was already validated by the human during those upstream phases.
When to Use This Skill
- After completing a writing project and wanting to preserve research for future use
- After gap-filling research during research-intake that should be saved permanently
- When a produced article should link back to its source notes in the vault
- When domain whirlybirds should be saved as persistent reference artifacts
- When synthesized connections or insights emerged during writing that should be captured
- When enriching a knowledge base with citation metadata from content creation
- At the end of a content strategy cycle to close the feedback loop
- When consolidating scattered research notes into structured vault entries
- When a content cluster is complete and cross-references between articles need permanent capture
- When domain expertise accumulated over multiple articles should be formalized as reference material
Core Workflow
- Identify artifacts to capture -- Review the outputs from the completed writing phases. Catalog what should be captured: research sources from gap-filling, connections discovered during content creation, domain whirlybirds, and article-to-source links. Present the catalog to the human for confirmation. Do not assume everything should be captured -- the human decides what has lasting value.
What ships with it
2 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.
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 · 130 lines · 38 tokens per session scan A f5d97344aaa2
knowledge-harvester is a skill published in the GitHub repository Jeffallan/writing-with-agents (30 stars, last pushed 2mo ago), licensed MIT. It adds 38 tokens to every session and 1,769 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 2026-08-30.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
shellm
Reference for the shellm system — recursive LLM shell, identity management, memory, skills, trajectory, and all CLI tools. Use when working on shellm itself, debugging agent behavior, or understanding how the pieces fit together.