whyguard AGENTS.md

Repository instructions for whyguard, a TypeScript and JavaScript tool whose design and evidence rules are documented across its project files.

In plain words
What is it for?
Use them when planning or implementing whyguard features, especially changes involving its code structure, data pipeline, language support, or historical explanations.
Why use it?
They tell coding agents where to find product, architecture, structure, and evidence policies, while preventing unsupported claims and unapproved architectural changes.

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/rosselps/whyguard/agents-md
Clone the repo
git clone --depth 1 https://github.com/rosselps/whyguard

Made for: Codex, OpenCode.

Per session 4,673 This file is loaded in full into every session.
When invoked 4,673 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 $0.04673 $0.04673
Opus 5 $0.02337 $0.02337
Sonnet 5 $0.00935 $0.00935
Haiku 4.5 $0.00467 $0.00467

Measured yesterday against content hash 586e83a7b3da, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

whyguard 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 yesterday.

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 · 302 lines

How it starts

The opening of the file, as written. The whole thing — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Development context for any coding agent working in this repository. Kiro and compatible agents load it automatically, alongside .kiro/steering/.

Where the detail lives:

Topic File
What the product is and is not .kiro/steering/product.md
Components, pipeline, trust boundaries docs/architecture/architecture.md
Evidence strength, confidence, block rule .kiro/steering/evidence-policy.md
Package layout and dependency rules .kiro/steering/structure.md
What the tool reads from a repository docs/guides/feeding-whyguard.md
Coding standards and commit conventions CONTRIBUTING.md

Operating rules

  1. Read .kiro/steering/ before proposing architecture changes.
  2. Preserve the modular-monolith, ports-and-adapters boundary (domainapplication → adapters → apps).
  3. Do not add a new service, database, framework, or integration without an ADR.
  4. Do not expand language support beyond TypeScript/JavaScript in the MVP.
  5. Do not build an IDE extension.
  6. Prefer deterministic Git/AST logic before LLM logic.
  7. Never claim a historical reason without evidence IDs.
  8. Distinguish protected behavior from current implementation.
  9. Never auto-execute generated tests.
  10. Keep GitHub permissions minimal — Contents/Pull requests/Issues/Metadata Read, Checks Read & Write only. Never request Contents Write for the App.
  11. Keep the CLI functional as a fallback — it remains a first-class surface alongside the MCP server.
  12. Include tests for every new detector or risk rule.
  13. Return unknown when evidence is weak; never invent an incident, issue, or reason.
  14. Do not weaken webhook, path, command, or secret-handling controls.
  15. Before finishing a task, run pnpm typecheck, pnpm lint, pnpm format:check, and relevant tests.
  16. The .kiro/settings/mcp.json and .kiro/hooks/*.template files in this repo are templates for a target workspace being protected by WhyGuard — never register a live PreToolUse hook against WhyGuard's own repository.

Read the full file on GitHub · 302 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. yesterday First seen · 302 lines · 4,673 tokens per session scan A 586e83a7b3da

Subscribe to this mod's changes

whyguard AGENTS.md is an instructions file published in the GitHub repository rosselps/whyguard (0 stars, last pushed 1mo ago), licensed MIT. It adds 4,673 tokens to every session, about $0.0234 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.