ruleblast AGENTS.md

ruleblast AGENTS.md is an instructions file for Codex, OpenCode from Kpoiut/ruleblast. It costs 355 tokens per session, scanned A, original, Apache-2.0.

A set of repository rules for RuleBlast, a local read-only debugger that shows which project instructions apply to a given code surface. It requires documented evidence and preserves uncertainty when the available evidence is incomplete.

In plain words
What is it for?
Use it when changing RuleBlast's instruction-resolution logic, profiles, snapshots, impact analysis, canonicalization, rendering, tests, or documentation.
Why use it?
It prevents unsupported conclusions about how repository instructions or agents behave and keeps debugging changes within the project's documented boundaries.

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/kpoiut/ruleblast/agents-md
Clone the repo
git clone --depth 1 https://github.com/Kpoiut/ruleblast

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 ruleblast AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kpoiut/ruleblast/agents-md.svg)](https://agentmods.dev/instructions/kpoiut/ruleblast/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/kpoiut/ruleblast/agents-md"><img src="https://agentmods.dev/badge/instructions/kpoiut/ruleblast/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 355 This file is loaded in full into every session.
When invoked 355 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 $0.00355 $0.00355
Opus 5 $0.00178 $0.00178
Sonnet 5 $0.00071 $0.00071
Haiku 4.5 $0.00036 $0.00036

Measured 4d ago against content hash fa5c37a0ae98, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ruleblast 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 4d 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 · 33 lines

What it actually says

RuleBlast repository instructions

RuleBlast is a small, local, read-only debugger for repository instruction projection. Keep every change inside the public boundary in CONTRACT.md and the active maturity gate in ROADMAP.md. Agents working in this checkout: .agents/skills/ruleblast/SKILL.md.

Evidence before confidence

  • Model only documented repository-loading semantics for one named surface and revision.
  • Pin an official URL or implementation revision, retrieval date, and exact claim for resolver behavior.
  • Preserve PARTIAL, UNKNOWN, UNSPECIFIED, RUNTIME_DECIDED, and INDETERMINATE when evidence does not justify certainty.
  • Label synthetic public metrics DEMO FIXTURE before their first appearance.
  • Never infer model compliance or response behavior from a repository projection.

Change discipline

  • Write the failing behavior test first and confirm the intended failure.
  • Implement the smallest complete behavior, then simplify changed code.
  • Keep vendor logic in profile adapters; snapshots, impact, canonicalization, and rendering stay profile-neutral.
  • Do not add a fifth action, product UI, hosted component, network/model call, telemetry, mutation, auto-fix, or executable profile extension.
  • Avoid duplicate adapters and wrappers that only rename an existing operation.
  • Keep one production source module under 400 lines unless an extraction review justifies otherwise.

Before a commit

Run focused tests, then:

npm run check
npm run build
git diff --check

Use a Conventional Commit subject. Update public docs only for behavior that is merged and verified; label incomplete work with the roadmap vocabulary.

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. 4d ago First seen · 33 lines · 355 tokens per session scan A fa5c37a0ae98

Subscribe to this mod's changes

ruleblast AGENTS.md is an instructions file published in the GitHub repository Kpoiut/ruleblast (19 stars, last pushed 10d ago), licensed Apache-2.0. It adds 355 tokens to every session, about $0.0018 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.