agentic-kb AGENTS.md

agentic-kb AGENTS.md is an instructions file for Codex, OpenCode from wlfghdr/agentic-kb. It costs 3,289 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for agentic-kb, a project that maintains system specifications and related documentation rather than the production system itself.

In plain words
What is it for?
Use them when editing agentic-kb specifications or concept documents so changes follow the project’s documentation, neutrality, and changelog requirements.
Why use it?
They establish rules such as writing specifications before implementation, avoiding dependence on one vendor, and recording changes with versions.

Instructions file for CodexOpenCode

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/wlfghdr/agentic-kb/agents-md
Clone the repo
git clone --depth 1 https://github.com/wlfghdr/agentic-kb

Made for: Codex, OpenCode.

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.

agentmods badge for agentic-kb AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/wlfghdr/agentic-kb/agents-md.svg)](https://agentmods.dev/instructions/wlfghdr/agentic-kb/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/wlfghdr/agentic-kb/agents-md"><img src="https://agentmods.dev/badge/instructions/wlfghdr/agentic-kb/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,289 This file is loaded in full into every session.
When invoked 3,289 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.

ModelPer sessionOnce invoked
Fable 5 $0.03289 $0.03289
Opus 5 $0.01644 $0.01644
Sonnet 5 $0.00658 $0.00658
Haiku 4.5 $0.00329 $0.00329

Measured 3d ago against content hash f81b0194c3a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentic-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 3d 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 · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instructions

Version: 0.15 | Last updated: 2026-06-02

This file is read first by any AI agent (and any human) working in this repository. It defines the ground rules. Layer-specific documents in docs/ extend these rules — they never override them.

This repo is a specification, not a product. Work done here is documentation work: precise, versioned, cross-referenced. Code exists only to validate docs (CI).


Rules

1. Spec-first, implementation-later

This repo defines what the system does and how it is shaped. It does not build it. Implementations live in companion repos. If a PR here proposes runtime code beyond CI tooling, reject it.

2. No vendor lock-in

The spec must remain IDE-agnostic, harness-agnostic, and vendor-neutral. Examples are welcome. Hardcoded product names, company names, or proprietary service references are not. The CI guards against a small list of forbidden terms; reviewers guard against the rest.

3. Every change is a versioned change

Any edit to a spec/concept doc MUST:

  • append a row to that file's own ## Changelog section (when the file has one — see "Which files have a per-file changelog" below),
  • add a line under ## [Unreleased] in the root CHANGELOG.md,
  • bump the relevant version field if the change alters semantics (see CHANGELOG.md for PATCH/MINOR/MAJOR rules).

Which files have a per-file changelog (and which do not):

File category Per-file ## Changelog? Why
Skill specs (plugins/kb/skills/*/SKILL.md) and skill references (plugins/kb/skills/*/references/*.md) yes They are standalone behavioral spec docs that adopters version-pin
Agent specs (plugins/kb/agents/*.md) yes Same reason
docs/REFERENCE.md, docs/collaboration.md, docs/concurrency.md, docs/operating-model.md, docs/role-handbook.md, docs/glossary.md, docs/first-run-acceptance.md yes Each is a standalone normative doc
docs/roadmap.md, docs/examples/*.md yes (recommended) Tracks how the example or roadmap drifted
AGENTS.md, CONTRIBUTING.md, CODE_OF_CONDUCT.md, SECURITY.md yes Long-lived governance docs
README.md no The root CHANGELOG.md is the single source of truth for the release narrative the README points at. A per-file changelog block on the README duplicates CHANGELOG.md and ages badly. The README footer links to CHANGELOG.md instead
Inline format examples inside fenced markdown blocks (e.g. the ## Changelog lines inside Topic / Brief / Spec format examples in docs/REFERENCE.md §4) no Those ## Changelog lines document that the file format requires an inline changelog. They are spec content, not changelogs of the enclosing doc
Templates under plugins/**/templates/ no Templates are scaffolded into adopter KBs; they carry their own inline changelog placeholders for the artifact they instantiate, not for the template
Generated artifacts (index.html, dashboard.html, plugin manifests under plugins/*/plugin.json) no Generated; the source they regenerate from carries the changelog

Read the full file on GitHub · 128 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.

  1. 3d ago First seen · 128 lines · 3,289 tokens per session scan A f81b0194c3a4

Subscribe to this mod's changes

agentic-kb AGENTS.md is an instructions file published in the GitHub repository wlfghdr/agentic-kb (10 stars, last pushed 18d ago), licensed Apache-2.0. It adds 3,289 tokens to every session, about $0.0164 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.