skill-runtime-intelligence AGENTS.md

Project instructions for a local-first tool that observes coding-agent runs and produces an evidence-graded overview of what happened.

In plain words
What is it for?
They guide read-only event collection, local storage, evidence labels, versioned integrations, and the product's user interface and scope.
Why use it?
They prevent the tool from taking over agent work, exposing sensitive data, or presenting guesses as proven causes or results.

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/hellogxp/skill-runtime-intelligence/agents-md
Clone the repo
git clone --depth 1 https://github.com/hellogxp/skill-runtime-intelligence

Made for: Codex, OpenCode.

Per session 270 This file is loaded in full into every session.
When invoked 270 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 $0.00270 $0.00270
Opus 5 $0.00135 $0.00135
Sonnet 5 $0.00054 $0.00054
Haiku 4.5 $0.00027 $0.00027

Measured yesterday against content hash 10d7bd8991b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-runtime-intelligence 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 · 35 lines

What it actually says

Project instructions

Product

This repository builds a local-first Agent Skill runtime intelligence tool. Its first outcome is an evidence-graded Skill Run Panorama.

Read these documents before changing product behavior:

  1. docs/product-definition.md
  2. docs/mvp-specification.md
  3. docs/runtime-event-model.md
  4. docs/ui-information-architecture.md

Non-negotiable principles

  • Observe agent runs; do not take over or orchestrate them.
  • Default to read-only collection and local storage.
  • Do not proxy model requests.
  • Do not block agent actions in the default product.
  • Never store secrets or raw sensitive content unnecessarily.
  • Label evidence as Observed, Derived, Inferred, or Experimental.
  • Never claim causal Skill effectiveness from one run.
  • Preserve raw source events separately from normalized and inferred records.
  • Keep each agent integration behind a versioned adapter.

Scope discipline

The MVP is not a Skill marketplace, registry, security gate, universal runtime, or general LLM observability platform. New features must strengthen the Skill-specific run panorama or diagnosis workflow.

Verification and UI

  • Do not use, inspect, invoke, or depend on StateSeal in this repository.
  • Do not require StateSeal receipts or StateSeal verification for development, experiments, delivery, or release reporting.
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 · 35 lines · 270 tokens per session scan A 10d7bd8991b2

Subscribe to this mod's changes

skill-runtime-intelligence AGENTS.md is an instructions file published in the GitHub repository hellogxp/skill-runtime-intelligence (7 stars, last pushed 21d ago), licensed Apache-2.0. It adds 270 tokens to every session, about $0.0014 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.