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 agentmods add skills/waelmas/codeplow/obsidian-kbnpx skills add waelmas/codeplow --skill obsidian-kbgit clone --depth 1 https://github.com/waelmas/codeplowWrote 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/waelmas/codeplow/obsidian-kb)<a href="https://agentmods.dev/skills/waelmas/codeplow/obsidian-kb"><img src="https://agentmods.dev/badge/skills/waelmas/codeplow/obsidian-kb.svg" alt="Measured on agentmods" 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 | $0.00130 | $0.05371 |
| Opus 5 | $0.00065 | $0.02686 |
| Sonnet 5 | $0.00026 | $0.01074 |
| Haiku 4.5 | $0.00013 | $0.00537 |
Grade A, and why
obsidian-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 4d 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 — 436 lines — stays where its author put it; the contents beside it link to each section on GitHub.
obsidian-kb - Project Knowledge Base Lifecycle
This plugin gives AI coding agents persistent memory across sessions via Obsidian vaults. It provides seven skills (also available as slash commands in Claude Code and Cursor; /kb-offboard has a /kb-handoff alias):
| Skill / Command | When to trigger |
|---|---|
kb-init / /kb-init |
Full initialization: scaffold + populate vault with codebase analysis + audit existing project markdown for stale claims. Use when user wants project memory set up properly from the start. |
kb-scaffold / /kb-scaffold |
Empty scaffold only (no codebase analysis). Use when user explicitly wants to manage content manually. Most users should use /kb-init. |
kb-audit / /kb-audit |
Re-runnable doc freshness audit. Scan project markdown against current code, flag stale claims with file:line evidence. Use for quarterly doc refreshes, before major rewrites, or when user says "are our docs still accurate?". |
kb-update / /kb-update |
Refresh KB notes inside the vault to reflect recent code changes. Surgical evidence-backed edits, flags new concepts as candidates. Use after a significant refactor, before /kb-offboard, or when the KB has drifted from the code. Complements /kb-audit — vault scope vs. project scope. |
kb-onboard / /kb-onboard |
Start of a session when a vault exists for this project. |
kb-offboard / /kb-offboard (alias /kb-handoff) |
End of a session, user says "done", "wrapping up", "that's it". |
kb-graph / /kb-graph |
User wants to visualize the knowledge base as a graph in Obsidian. |
When to Nudge
Do suggest kb-onboard early in a session if you detect a vault exists for the current project. A simple "This project has a knowledge vault - want me to trigger kb-onboard (or run /kb-onboard) to see what happened last session?" is enough.
Do suggest kb-offboard when the user signals they're wrapping up. Don't wait for them to ask - they may not know the skill exists.
What ships with it
3 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.
- 4d ago First seen · 436 lines · 130 tokens per session scan A d906a6ac26ab
obsidian-kb is a skill published in the GitHub repository waelmas/codeplow (8 stars, last pushed 4mo ago), licensed MIT. It adds 130 tokens to every session and 5,371 once invoked, about $0.0006 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
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…
auditing-subgroup-fairness
Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
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…