wherefore AGENTS.md

Repository instructions for maintaining wherefore, a plain-Markdown record of technical decisions, questions, and plans. They define where these records belong and how agents should read and update them.

In plain words
What is it for?
Use them when reading past decisions, recording a new choice, tracking an open question, or adding a forward-looking plan under the wherefore/ directory.
Why use it?
They keep decisions and unresolved questions in one consistent place, so future contributors can understand why technical choices were made.

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/dustinvk/wherefore/agents-md
Clone the repo
git clone --depth 1 https://github.com/DustinVK/wherefore

Made for: Codex, OpenCode.

Per session 2,269 This file is loaded in full into every session.
When invoked 2,269 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 $0.02269 $0.02269
Opus 5 $0.01135 $0.01135
Sonnet 5 $0.00454 $0.00454
Haiku 4.5 $0.00227 $0.00227

Measured 2d ago against content hash 25ee9373070a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

wherefore 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 · 203 lines

How it starts

The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.

wherefore: agent instructions

This repo uses a wherefore/ directory: a plain-markdown record of technical decisions (what was chosen, why, what was rejected) and open questions. Any agent can read and maintain it by following the rules below. Do not invent a second location; if wherefore/ exists, use it.

Directory layout

wherefore/
  topics.md         controlled tag vocabulary: Areas and Topics
  log/YYYY-MM-DD-short-slug.md    one decision per file
  questions/Q-NNN-short-slug.md   one question per file (ID prefix + scannable slug)
  plan/P-NNN-short-slug.md        forward-looking plan items, one per file

If wherefore/ does not exist, create it plus log/, questions/, a starter topics.md, and a README.md containing exactly:

# wherefore

A decision log in plain markdown. Each file captures what was decided, why, and what was ruled out.

Maintained by the [wherefore](https://github.com/DustinVK/wherefore) skill.

Reading (answering "why did we...", "what did we decide about...")

  1. Read only the leading frontmatter block of every log/*.md file (it is short), and shortlist by area, topic, story, or title. Then open only the shortlisted files (1-5), not the whole log. The frontmatter also carries each entry's status and superseded_by, so filtering and chain-following need nothing else.
  2. Treat status active, current, or absent as current. For a superseded entry, follow its superseded_by slug to the replacement (repeat until you reach an active entry). Exclude obsolete entries unless asked about history.
  3. Answer from active entries, lead with the current decision, cite the source by date + title + filename. If nothing matches, say so plainly. Never fabricate.
  4. After answering, read the questions/Q-*.md frontmatter and surface briefly any open questions whose areas overlap.

Writing a decision (capture)

Distill the discussion to its useful residue; do not transcribe. Write wherefore/log/YYYY-MM-DD-short-slug.md (slug: short, lowercase, hyphenated) with this EXACT frontmatter and section structure:

Read the full file on GitHub · 203 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. 2d ago First seen · 203 lines · 2,269 tokens per session scan A 25ee9373070a

Subscribe to this mod's changes

wherefore AGENTS.md is an instructions file published in the GitHub repository DustinVK/wherefore (1 stars, last pushed 1mo ago), licensed MIT. It adds 2,269 tokens to every session, about $0.0113 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.