A command-line and search workflow for finding relevant sections in a project's stored Markdown knowledge base, such as notes, decisions, meeting records, and archived changes.

Use it before planning a change, asserting that no precedent exists, or deciding which parts of a large set of project notes to read.

A simple text search can return too many files or miss earlier decisions. Ranked section results help an agent check existing knowledge before planning work or making claims.

How tatargabor/set-core configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to tatargabor/set-core. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/tatargabor/set-core/main/.claude/skills/set/kb/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/tatargabor/set-core

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/tatargabor/set-core/kb/github.svg)](https://agentmods.dev/skills/tatargabor/set-core/kb)

Your own site

<a href="https://agentmods.dev/skills/tatargabor/set-core/kb"><img src="https://agentmods.dev/badge/skills/tatargabor/set-core/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/tatargabor/set-core/kb"><img src="https://agentmods.dev/badge/skills/tatargabor/set-core/kb.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 523 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00064	$0.00523
Opus 5.5	$0.00026	$0.00209
Sonnet 5.5	$0.00013	$0.00105
Haiku 4.5	$0.00006	$0.00052

Measured 11d ago against content hash 29e770ac924b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

set: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 11d 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.

.claude/skills/set/kb/SKILL.md · 46 lines

What it actually says

set:kb — the project knowledge base

set-kb searches every indexed markdown file of THIS project and returns ranked SECTIONS with a score — not files. The kb_search / kb_get MCP tools run the same engine; this skill is the manual, per-command way in.

When to search

Before claiming there is no source, precedent or prior decision — search first.
Before planning a change: the topic may already be decided, tried or measured.
When a grep returns more files than you will read — the ranking has already done that work.

How to search

set-kb search "<topic words>"                      # the text page
set-kb search "<topic words>" --json               # the stable contract for scripts
set-kb search "<topic>" --root <root>              # narrow to one configured root
set-kb search "<topic>" --channel <name>           # …or one channel
set-kb search "<topic>" --scope <name>=<value>     # …or one captured scope
set-kb search "<topic>" --exclude-path <fragment>  # drop a path from the page

How to read a hit

path is repository-relative and set-kb get <path> accepts it unchanged; set-kb get <path> --section "<heading path>" prints that section verbatim.
headingPath locates the section; suppressedSections counts further matching sections of the same file; duplicateCount marks identical content at other paths.
channel and scope say which configured layer a hit came from — set-kb sources lists them with the project's own descriptions.
score is BM25 (lower = better); compare only within one result page.

What zero hits means

Zero hits describe THE INDEX, not the world. The page says so, names the exact query, and lists the exclusions in force. When a corpus looks wrong run set-kb doctor; when a specific document must be findable run set-kb findability.

Changes

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.

11d ago First seen · 46 lines · 64 tokens per session scan A 29e770ac924b

Subscribe to this mod's changes

set:kb is a skill published in the GitHub repository tatargabor/set-core (36 stars, last pushed 13d ago), licensed MIT. It adds 64 tokens to every session and 523 once invoked, about $0.0003 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 2026-10-09.

Autonomous Agents Orchestration Research cli git-worktree mcp

drug-design

End-to-end drug discovery pipeline orchestration. Deterministic Python script that auto-chains structure prediction, pocket detection, de novo design, docking, scoring, and ADMET filtering into reproducible workflows.

synthetic-sciences/openscience · 44 tokens

atmos-components

Component architecture: Terraform root modules, remote source provisioning, abstract components, component inheritance, versioning, mixins, catalog patterns.

cloudposse/atmos · 29 tokens

atmos-design-patterns

Design patterns: stack organization, component catalogs, inheritance, configuration composition, version management, layered configuration.

cloudposse/atmos · 25 tokens

atmos-helmfile

Helmfile orchestration: sync/apply/destroy/diff, Kubernetes deployments, declarative Helm plugins, varfile generation, EKS integration, source management.

cloudposse/atmos · 38 tokens

atmos-scaffold

Scaffold templates: authoring scaffold.yaml, form fields (types, validation, conditional when:), conditional file generation, step-backed hooks (pre/post-generate), update-safe 3-way merge, and atmos scaffold generate/list/validate.

cloudposse/atmos · 52 tokens

atmos-starlark

Write Atmos Automation Language scripts (Python-like, embedded Starlark): standalone executable tools (atmos ./deploy.star, #!/usr/bin/env atmos, typed flags via cli.command), type: script steps in workflows, custom commands, and hooks, parallel tasks, retries, and migration of Bash/Python glue. Reach for it when a…

cloudposse/atmos · 136 tokens

set-core: Skill for Claude Code