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 uttambharadwaj/kb-graph --skill kb-workflowgit clone --depth 1 https://github.com/uttambharadwaj/kb-graphWrote 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/uttambharadwaj/kb-graph/kb-workflow)<a href="https://agentmods.dev/skills/uttambharadwaj/kb-graph/kb-workflow"><img src="https://agentmods.dev/badge/skills/uttambharadwaj/kb-graph/kb-workflow/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/uttambharadwaj/kb-graph/kb-workflow"><img src="https://agentmods.dev/badge/skills/uttambharadwaj/kb-graph/kb-workflow.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 | $0.00040 | $0.01465 |
| Opus 5.5 | $0.00016 | $0.00586 |
| Sonnet 5.5 | $0.00008 | $0.00293 |
| Haiku 4.5 | $0.00004 | $0.00146 |
Grade A, and why
kb-workflow 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 1mo 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Base Workflow
What This Skill Does
This skill teaches you how to use the knowledge-base-server MCP tools efficiently. It does NOT replace the MCP server — it complements it by giving you the retrieval strategy that saves 90%+ tokens.
Think of it this way:
- MCP server = the engine (search, read, write, capture)
- This skill = the driving instructions (when to search, what to read, how to capture)
Before Starting Any Task
Search the KB for relevant context BEFORE writing code or making decisions:
1. kb_context("topic") — get summaries only (~100 tokens per doc, 90% savings)
2. Review titles and summaries — decide which docs matter
3. kb_read(id) — read full content ONLY for docs you actually need
Never skip this. The KB has accumulated lessons, fixes, decisions, and architecture docs. Searching first prevents:
- Repeating solved problems
- Contradicting past decisions
- Missing known pitfalls
- Wasting tokens on re-discovery
The Three-Tier Retrieval Pattern
The KB has three tiers of information. Query the right tier for your need:
| Need | Tool | Tokens | When |
|---|---|---|---|
| Quick context | kb_context |
~100/doc | Always start here |
| Specific search | kb_search |
~200/result | Looking for something specific |
| Conceptual match | kb_search_smart |
~200/result | Fuzzy/semantic queries |
| Full document | kb_read |
~500-5000/doc | Only after context confirms relevance |
Rule: Never kb_read without kb_context first. You wouldn't read an entire book to check if it's relevant — you'd read the summary.
- Fallback: if
kb_searchcomes up empty, grep the vault directly — it is plain markdown on disk. Find the vault path in the kb-graph install's.env(OBSIDIAN_VAULT_PATH=), default~/kb-vault, thengrep -ri "<term>" <vault-path>. Retrieval ranking can miss sparse signals; direct inspection of raw files is the reliable backstop.
After Completing Work
Capture what you learned so the next session starts smarter:
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.
- 1mo ago Changed · +6 lines 5daa3aa929db
- 1mo ago First seen · 139 lines · 40 tokens per session scan A 2e836c745cd5
kb-workflow is a skill published in the GitHub repository uttambharadwaj/kb-graph (4 stars, last pushed 18d ago), licensed MIT. It adds 40 tokens to every session and 1,465 once invoked, about $0.0002 per session on Opus 5.5. 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
knowit
Persistent, structured project memory for AI coding agents via the Knowit MCP server. Use before planning or editing code to load relevant rules, architecture, decisions, patterns, and conventions; use after finishing work to save durable learnings. Triggers on "remember this", "what are our conventions", "project…
openakashic
Persistent memory for AI agents across sessions. Search what others figured out, write what you learn, publish what deserves a wider audience.
openlore
Query and publish to an OpenLore knowledge repository over SSH using ordinary shell commands. Use when a task needs project documentation, runbooks, shared team knowledge, or a place to publish findings.
memory
Persist and retrieve agent memory across sessions — recall via the three-stage protocol (structure route → semantic search → navigation fallback), read via memoryload, see the wiki structure via memorybrowse, write well-placed pages via memorywrite (including section-level append/rewrite), maintain via memorycurate.…
memory-dream
Curate the workspace memory wiki as its appointed orchestrator. Trigger on a Cloud-scheduled Dream task or a user's direct curation request. Inspect candidates for orphan leaves, near-duplicates, stale pages, remote conflicts and oversized hubs; browse the graph, cluster leaves into INDEX/hub/leaf structure, maintain…
conversation-compaction
Produce the SESSION PROJECTION of memory for an aging conversation slice. Runs as a single background model call (mirroring the memory extract hook) with NO live memory tools — durable capture to memory is extract's job. You MATCH the slice's durable facts to the memory pages you're handed (recall-found ) and emit…