Investigations¶
Longer investigations, recorded as findings rather than conclusions. Read these when you want the evidence a decision was made on.
A finding is the cheap neighbour: something that cost time once, written so the next encounter is short. An investigation costs more, and is read against the decision it fed rather than on its own.
A survey is a claim about what existed when it was written, so read one against its generated
date. Where an investigation deliberately stops short of choosing, it says so.
- Open Knowledge Format (OKF): findings - what the format these pages are written in actually specifies
- Substrate options for an OKF-based agent-first LLM wiki: investigation - the survey of tools that could hold such a knowledge base, deliberately stopping short of choosing
- Agent-integration layer and multi-vault interaction for an OKF-conformant PKB - how an agent reaches these pages, and how several bundles at different privacy tiers meet
- Federated OKF knowledge bases: a workspace-manifest architecture - the architecture that answered the previous two, and that this bundle is now an instance of
- Security Analysis of Agent Wiki (awiki) - a read of one such tool's source, asking what it does with your data
- skills.sh: repository layout, selective install and telemetry - where the skills installer looks, how a user takes one skill rather than all, and what it reports back
- Sharing one user-level AGENTS.md across harnesses - a crowded tool category that almost entirely refuses to write to the home directory, and why
- Spell-checking prose in a pre-commit hook - why two spell checkers catch different mistakes, and the one word that shows it
Backlinks¶
The following pages link to this page:
- Agent-integration layer and multi-vault interaction for an OKF-conformant PKB
- Federated OKF knowledge bases: a workspace-manifest architecture
- Index
- Open Knowledge Format (OKF): findings
- Security Analysis of Agent Wiki (awiki)
- Sharing one user-level AGENTS.md across harnesses
- Spell-checking prose in a pre-commit hook: corpus checkers, dictionary checkers, and what each one misses
- Substrate options for an OKF-based agent-first LLM wiki: investigation
- skills.sh: repository layout, selective install and telemetry