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/zmij/agent-kb/kb-setupnpx skills add zmij/agent-kb --skill kb-setupgit clone --depth 1 https://github.com/zmij/agent-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/zmij/agent-kb/kb-setup)<a href="https://agentmods.dev/skills/zmij/agent-kb/kb-setup"><img src="https://agentmods.dev/badge/skills/zmij/agent-kb/kb-setup.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 | $0.00076 | $0.01012 |
| Opus 5 | $0.00038 | $0.00506 |
| Sonnet 5 | $0.00015 | $0.00202 |
| Haiku 4.5 | $0.00008 | $0.00101 |
Grade A, and why
kb-setup scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -o /dev/null -w '%{http_code}' http://localhost:6333/healthz # 200 = already up How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
KB Setup
Goal: from "plugin installed" to "kb_search answers from this repo's docs" with as little user effort as possible. Work through the steps in order; each is idempotent, so re-running the skill on a half-configured repo is safe.
0. Locate the plugin checkout
Some fallbacks below need the plugin's own files:
KB_PLUGIN="${CLAUDE_PLUGIN_ROOT:-$(ls -d ~/.claude/plugins/cache/agent-grounding/agent-kb/*/ 2>/dev/null | sort -V | tail -1)}"
1. Preflight
uv --version # required — stop and tell the user to install uv if missing
docker info >/dev/null 2>&1 || echo "DOCKER-DOWN"
If Docker is down/absent, stop: Qdrant needs it (or the user must provide
a reachable Qdrant and set QDRANT_HOST/QDRANT_GRPC_PORT).
2. Qdrant
Check, then start only if needed (idempotent):
curl -s -o /dev/null -w '%{http_code}' http://localhost:6333/healthz # 200 = already up
docker run -d --name qdrant \
-v qdrant_storage:/qdrant/storage \
-p 6333:6333 -p 6334:6334 qdrant/qdrant
If the container name exists but is stopped: docker start qdrant.
3. kb.yaml
If the repo root already has one, skip ahead. Otherwise author it:
-
Survey the repo briefly: where does prose documentation live (
docs/,doc/,documentation/, a wiki subtree)? Is there aMakefilewithtarget: ## descriptioncomments? Is there an ontology directory (rare on first setup — don't invent one)? -
Draft a minimal config — markdown sources for real doc trees, plus
make_targetsonly if documented targets exist:project: <repo-name> sources: docs: type: markdown root: docs -
Confirm the draft with the user before writing (one question: doc roots to include). Then write it to
<repo-root>/kb.yaml.
Full field reference: $KB_PLUGIN/kb.example.yaml.
4. First index
Preferred — through the MCP tools if the agent-kb server is connected:
call kb_reindex per source (or ask it to run all), then kb_list_sources.
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 · 107 lines · 76 tokens per session scan A bbc31c9bf307
kb-setup is a skill published in the GitHub repository zmij/agent-kb (2 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 1,012 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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…