What is kb AGENTS.md?

Repository instructions for a knowledge base for coding agents, built from Markdown notes, links between notes, semantic search, and Git history. They describe its source code, workflows, public skill, internal processes, and tests.

Use them when querying or updating the knowledge base, capturing notes, creating plans, running agent workflows, auditing repository memory, or validating the package.

They show where the knowledge base, agent workflows, and implementation rules live. This helps changes preserve links, search behavior, repository context, and safe note editing.

kb AGENTS.md — Instructions file by hraness

Install

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.

agentmods

npx agentmods add instructions/hraness/kb/agents-md

Clone the repo

git clone --depth 1 https://github.com/hraness/kb

Made for: Codex, OpenCode.

Per session 2,494 This file is loaded in full into every session.

When invoked 2,494 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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	$0.02494	$0.02494
Opus 5	$0.01247	$0.01247
Sonnet 5	$0.00499	$0.00499
Haiku 4.5	$0.00249	$0.00249

Measured 2d ago against content hash 05c2be76a8ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

kb AGENTS.md 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 2d 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.

AGENTS.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

src/ – deterministic Markdown graph and attachment analysis, typed metadata and exact repository-scope queries, local hybrid retrieval, bounded Git provenance, code-mode sessions and DAG workflows, frozen-corpus evaluation authoring and execution, safe single-note authoring, percolation, repository-memory routing and audits, the advisory source inbox, structural navigation, initialization, CLI, capture, URL intelligence, and diagnostic code with colocated tests.
src/workflows/ – reusable code-mode decision-context, change-explanation, and plan-radar workflows with bounded parallel execution.
dist/ – committed Bun-targeted ESM entrypoints plus the compiled Defuddle worker.
skills/kb/ – the single public Agent Skill for querying, capturing into, planning in, percolating, refreshing, and validating a hraness/kb vault, with focused workflow references loaded on demand.
.agents/skills/ – internal plan authoring, phased execution, implementation, and independent review workflows.
kb/ – this source repository's authored rationale, maintained synthesis, and implementation plans; it is separate from the package's graph implementation and fixtures.
WRITING.md and STYLE.md – internal and public prose contracts.
docs/ – design, capture, and agent-workflow documentation.
.github/workflows/ – read-only branch validation, stable-version-triggered and recovery-dispatched stage-only npm publication, and checks-gated immutable GitHub Release automation.
portfolio-inventory.json, scripts/check-portfolio-inventory.ts, and scripts/check-installed-command-docs.ts – canonical public package inventory and standalone public-command consistency gates.
README.md, CONTRIBUTING.md, SECURITY.md, and LICENSE – public usage, project policy, threat model, and terms.
package.json, tsconfig.json, and bun.lock – standalone package and frozen verification configuration.

Guidelines

Read the full file on GitHub · 56 lines

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.

2d ago First seen · 56 lines · 2,494 tokens per session scan A 05c2be76a8ec

Subscribe to this mod's changes

kb AGENTS.md is an instructions file published in the GitHub repository hraness/kb (13 stars, last pushed 2d ago), licensed MIT. It adds 2,494 tokens to every session, about $0.0125 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 2026-08-30.

Git and workflow Memory and context Testing agent-memory ai-agents bun knowledge-base local-first markdown

kb AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Contents

Guidelines

What this file has done since we first saw it

Other instructions, from other repositories

siyuan AGENTS.md

my-wiki AGENTS.md

Binder AGENTS.md

keepygaga AGENTS.md

agent-recall-trail AGENTS.md

memory-harbor AGENTS.md