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 wlfghdr/agentic-kb --skill kb-managementgit clone --depth 1 https://github.com/wlfghdr/agentic-kbWrote 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/wlfghdr/agentic-kb/kb-management)<a href="https://agentmods.dev/skills/wlfghdr/agentic-kb/kb-management"><img src="https://agentmods.dev/badge/skills/wlfghdr/agentic-kb/kb-management.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 5.1 | $0.00074 | $0.05666 |
| Opus 5 | $0.00037 | $0.02833 |
| Sonnet 5 | $0.00015 | $0.01133 |
| Haiku 4.5 | $0.00007 | $0.00567 |
Grade A, and why
kb-management 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 8d 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 — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: KB Management
This skill implements the agentic-kb specification. It operates on the user's workspace as a layer graph: one anchor layer with .kb-config/, plus any number of additional contributor or consumer layers connected by parent edges.
When to invoke
Invoke this skill whenever the user:
- Types
/kbfollowed by text, a URL, a file path, or a subcommand. - Mentions any feature keyword from the
triggers:list above, even without the/kbprefix — e.g. "let me capture this", "promote that finding to the team layer", "start my day", "open a decision on caching", "weekly status please". The harness fires the skill on those phrases; the skill is responsible for routing them to the right/kbflow and confirming the proposed action before mutating state. - Describes work that implies capture, digestion, promotion, publication, decision-making, note-taking, or artifact generation, even when no listed keyword appears verbatim.
- Needs a read-only triage summary across the current layer graph.
When the user invokes the skill via a feature keyword rather than /kb, the response MUST: name the inferred /kb … flow, restate the inferred target layer, and ask for confirmation before any mutation. Read-only flows (status, triage scans) may proceed immediately.
The single command model
There is one user-facing command: /kb. Infer layer and action from context:
| Input | Action |
|---|---|
| URL or pasted text | Capture into the current layer via the evaluation gate |
| File path inside a known layer | Operate in that layer context |
| Explicit layer name | Route to the named target layer |
Explicit subcommand (review, promote, digest, task, note, report, ...) |
Run that flow |
Bare /kb |
Read-only triage scan |
.kb-config/layers.yaml |
Declares the layer graph, roles, parent edges, marketplaces, and connections |
Full command reference: references/command-reference.md.
Concurrency contract: docs/concurrency.md defines the promote-collision, diverged-backlink, topic-merge, and append-only log cases that /kb sync and /kb audit reconcile.
What ships with it
34 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.
- references/audit.md 11 KB
- references/capture-routing.md 18 KB
- references/command-reference.md 22 KB
- references/connections-lifecycle.md 11 KB
- references/evaluation-gate.md 3.0 KB
- references/html-artifacts.md 24 KB
- references/output-contract.md 7.4 KB
- references/promote-contract.md 7.8 KB
- references/publish-contract.md 10 KB
- references/rituals.md 4.1 KB
- references/spec-summary.md 3.4 KB
- references/tracker-backed-primitives.md 14 KB
- scripts/generate_report.py 28 KB runs code
- scripts/migrate_archives.py 4.9 KB runs code
- scripts/migrate_layer_model.py 5.7 KB runs code
- templates/artifact-base.html 2.9 KB
- templates/backlog.md 100 B
- templates/brief.md 483 B
- templates/decision.md 480 B
- templates/finding.md 279 B
- templates/focus.md 238 B
- templates/idea.md 282 B
- templates/incident.md 397 B
- templates/index.html 6.2 KB
- templates/note.md 310 B
- templates/release.md 354 B
- templates/report-delivery.md 1.1 KB
- templates/report-roadmap-change.md 1.1 KB
- templates/report-status.md 1.1 KB
- templates/report.html 31 KB
- templates/retro.md 479 B
- templates/spec.md 518 B
- templates/topic.md 238 B
- templates/workstream.md 708 B
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.
- 8d ago First seen · 294 lines · 74 tokens per session scan A 75d4f78aca3a
kb-management is a skill published in the GitHub repository wlfghdr/agentic-kb (10 stars, last pushed 23d ago), licensed Apache-2.0. It adds 74 tokens to every session and 5,666 once invoked, about $0.0004 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
task-agent-eliza-bridge
Use when spawning a Claude Code, Codex, Gemini, Aider, or other CLI task agent whose work needs parent Eliza runtime context. Covers the read-only loopback bridge for character, room, memory, and active workspace state.
kb-builder
Build an Obsidian-compatible knowledge base from public web sources using the TinyFish CLI. Use this skill when a user wants a builder-grade markdown knowledge base on a technical topic, asks for a structured research vault, or wants a topic compiled from live public sources into interlinked markdown files. Supports…
self-improve-with-tinyfish
Enables Hermes to create new reusable skills for itself by researching live web sources with TinyFish Search and Fetch, analyzing source coverage, writing SKILL.md files, and installing them into Hermes memory. Use when the user asks Hermes to learn, teach itself, upgrade itself, or save a reusable capability.
wegent-knowledge
Knowledge base management and search tools for Wegent. Provides capabilities to list, create, update, and search knowledge bases and documents using RAG retrieval. Use this skill when the user wants to manage knowledge bases, documents, or search for information programmatically.
weknora-shared
Use when driving a WeKnora RAG server through the weknora CLI as an agent — authenticating, managing knowledge bases / documents / sessions / agents, running search or chat, or interpreting the CLI's JSON envelopes and exit codes. Read this before any other weknora- skill.
knowledge_base
Manage the user's personal knowledge base — knowledge graph, documents, and wiki vault.