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 oyi77/1ai-skills --skill kbgit clone --depth 1 https://github.com/oyi77/1ai-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/oyi77/1ai-skills/kb)<a href="https://agentmods.dev/skills/oyi77/1ai-skills/kb"><img src="https://agentmods.dev/badge/skills/oyi77/1ai-skills/kb/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/oyi77/1ai-skills/kb"><img src="https://agentmods.dev/badge/skills/oyi77/1ai-skills/kb.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00023 | $0.03863 |
| Opus 5 | $0.00012 | $0.01931 |
| Sonnet 5 | $0.00005 | $0.00773 |
| Haiku 4.5 | $0.00002 | $0.00386 |
Grade A, and why
kb 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 today.
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 — 518 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Base (KB)
Overview
The Knowledge Base (KB) is a PARA-structured persistent memory system for AI agents. It survives agent compactions, session boundaries, and context window limits by storing facts, decisions, architecture records, and project state in files on disk.
PARA stands for:
- Projects — active deliverables with deadlines
- Areas — ongoing responsibilities without end dates
- Resources — reference material, templates, cross-references
- Archives — stale content, git-preserved, never deleted
The KB works alongside the memory MCP tools (search_nodes, open_nodes,
read_graph, create_entities, add_observations, create_relations) and the
file-based scratchpad pattern. Use all three layers together:
| Layer | Scope | Persistence | Example |
|---|---|---|---|
| KB files | Long-term org memory | Indefinite (git) | ~/kb/projects/foo/facts.yaml |
| MCP knowledge graph | Relationship graph | Per-session + recall | Entities, relations, observations |
| Scratchpad file | Active session bridge | < 30 min | ~/.kb-session-context.md |
Workflow
The KB lifecycle follows a predictable loop across every agent session:
Session Start → Load Context → Check Decisions → Work & Capture → Log → Session End
Per-Session Loop
- Cold start — MCP server connects, scratchpad is checked for < 30 min state
- Load yesterday — last session's End-of-Session Summary is retrieved
- Open decisions — all facts with
status: openacross every category - Work — agent performs tasks, captures facts as they arise
- Log decisions — every resolved decision gets a fact with
status: confirmed - End-of-Session — summary written, scratchpad updated, git commit + brain save
Weekly Loop
- Archive projects untouched > 90 days
- Prune stale observations
- Rebuild entity cross-reference index
- Review open decisions for closure
- Verify all code blocks in KB skills parse correctly
Querying the Knowledge Base
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.
- today Changed · +7 lines c74d74c6e84c
- 7d ago First seen · 511 lines · 23 tokens per session scan A ada74b9a4f79
kb is a skill published in the GitHub repository oyi77/1ai-skills (12 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 3,863 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
workflow-extract
Baut aus einem Chatverlauf oder aus bestehenden Automatisierungs-Prompts (z. B. eines anderen Agenten-Systems) eine selbstlaufende, user-neutrale Workflow-Automatisierung: einen wiederkehrenden Prompt bzw. Automations-Skill für Cron/Schedule/Loop. Alias: automations-extractor. Nutze diesen Skill bei „mach daraus eine…
letter-hooker
Erweitert automation-self-care um Letter Hooks, Preflight-Bootloader, Dokument-Traversierungsregeln und selbstheilende Prompt-Kontext- Anreicherung für KI-Agenten und CLIs ohne native, ereignisgetriebene JSON-Lifecycle-Hooks (wie Antigravity / Gemini CLI). Nutzen, wenn ein Agent Preflight-Regeln injizieren, vor…
hive.colony-progress-tracker
Claim tasks, record step progress, and verify SOP gates in the colony SQLite queue. Applies when your spawn message includes a dbpath field.
persistent-notes
Save notes locally to /mnt/workspace/notes.json file. Use when user wants to "save a note" or "remember something".
cache
Use when the user wants to view, search, add, edit, prune, archive, or clear hyperflow memory entries. CRUD interface for .hyperflow/memory/ — never modifies source code, only memory files. Trigger with /hyperflow:cache, "show memory", "search memory for X", "clear memory", "what does hyperflow remember about Y".
hive.context-preservation
Proactively extract critical values from tool results into working notes before automatic context pruning destroys them.