llm-friendly-context

A guide for writing instructions that another AI agent can follow or judge without guessing.

In plain words
What is it for?
Use it for prompts, handoffs, plans, reviews, reports, task files, and other instructions meant for AI agents.
Why use it?
It turns vague requests into clear actions, inputs, decisions, success checks, and points where the agent should ask for help.

Skill for Claude CodeCodex

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 skills/shinpr/codex-workflows/llm-friendly-context
Any agent
npx skills add shinpr/codex-workflows --skill llm-friendly-context
Clone the repo
git clone --depth 1 https://github.com/shinpr/codex-workflows

Made for: Claude Code, Codex.

Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,066 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00052 $0.01066
Opus 5 $0.00026 $0.00533
Sonnet 5 $0.00010 $0.00213
Haiku 4.5 $0.00005 $0.00107

Measured 3d ago against content hash 9fafd2e99e98, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

llm-friendly-context 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/skills/llm-friendly-context/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LLM-Friendly Context

Purpose

Use this skill when writing or revising any content another agent will execute or judge: prompts, handoffs, planning artifacts, review findings, completion reports, generated instructions, test skeleton comments, work plans, and task files.

The goal is stable downstream execution. The next agent should know the target action, required inputs, accepted decisions, observable success criteria, and the condition that requires escalation.

Core Rules

  1. Use positive, executable instructions

    • State the action the next agent should perform.
    • Convert quality policies into observable acceptance criteria.
    • Keep a prohibition only when it protects an irreversible boundary or shipped contract. Name the protected condition and the allowed action.
    • Example: Preserve existing public API behavior across the documented compatibility cases.
  2. Make vague instructions concrete

    • Replace subjective terms with observable conditions, paths, commands, schemas, examples, or decision rules.
    • Terms that usually need clarification before handoff: appropriate, proper, related, existing behavior, optional, as needed, if needed, per convention, unresolved alternatives, TBD, and placeholder.
  3. Specify output shape

    • Define only the sections or fields the next consumer uses.
    • For agent handoffs, name produced artifact paths and the result needed by the next action. Require exact serialization only when a program parses it.
  4. Provide necessary context

    • Include purpose, source artifacts, hard constraints, accepted decisions, and unresolved conditions.
    • Prefer concrete file paths and section hints over broad module names.
    • Follow references only while they can change an in-scope decision, action, or verification result.
  5. Decompose complex work into verifiable steps

    • Expose dependency order when a later action relies on an earlier result.
    • Reuse one execution plan to retain all required steps and final verification during multi-step work. Simple, single-action work proceeds directly.

Read the full file on GitHub · 91 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 91 lines · 52 tokens per session scan A 9fafd2e99e98

Subscribe to this mod's changes

llm-friendly-context is a skill published in the GitHub repository shinpr/codex-workflows (38 stars, last pushed 5d ago), licensed MIT. It adds 52 tokens to every session and 1,066 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

ax-python-gen

Use when writing Python code with axllm for AxGen programs, forward calls, indexed multi-sampling, result pickers, streaming, tools, assertions, traces, usage, and output parsing.

ax-llm/ax · 46 tokens

ax-cpp-gepa

Use when writing C++ code with axllm for GEPA, Pareto tradeoffs, reflection clients, metric budgets, optimizer state, and artifacts.

ax-llm/ax · 39 tokens

llm-generation

LobeHub application-level LLM generation conventions. Use when adding or changing prompts, generateObject/generateText calls, structured output schemas, generation model selection, prompt versions, llmgenerationtracing scenarios, or tests for AI-generated business content. Do not use for provider adapter internals or…

lobehub/lobehub · 67 tokens

prompt-optimize

Expert prompt engineering skill that transforms Claude into "Alpha-Prompt" - a master prompt engineer who collaboratively crafts high-quality prompts through flexible dialogue. Activates when user asks to "optimize prompt", "improve system instruction", "enhance AI instruction", or mentions prompt engineering tasks.

labring/FastGPT · 61 tokens

calling-llms

Use when sending chat completions through liter-llm and routing to a specific provider via the provider/model prefix. Covers the chat call shape, provider routing, modelhint, message roles, and error categories.

xberg-io/liter-llm · 49 tokens

tool-calling

Use when defining functions/tools for an LLM to call through liter-llm, or requesting structured JSON outputs. Covers tool schemas, toolcalls handling, and response formats.

xberg-io/liter-llm · 39 tokens