happier: Skill for Claude Code

.agents/skills/happier-diagnose/SKILL.md

happier-diagnose is a skill for Claude Code, Codex from happier-dev/happier. It costs 90 tokens per session (1,611 once invoked), scanned A, original, MIT.

A read-only guide for investigating Happier runtime and support incidents using logs, diagnostics, runtime state, and source code.

In plain words
What is it for?
Use it to examine session, daemon, provider, authentication, connectivity, and runtime problems.
Why use it?
It helps identify the likely cause of failures without changing the repository during the investigation.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: installed under .agents/ (shared by several agents); mentions Codex; built for openclaw.

This is happier-dev/happier's own configuration. It tells Claude Code and Codex how to work on happier itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything happier configures →

About the project

Happier is an open-source, end-to-end encrypted client that lets people run AI coding-agent sessions on a computer and continue controlling them from a phone, browser, or desktop app. It is for developers who use agents such as Claude Code, Codex, Gemini, or OpenCode across multiple devices, with self-hosting available. The catalogue entries are add-ons for configuring or extending this client and its supported coding-agent workflows.

happier-dev/happier · 1,624 stars · on GitHub · happier.dev

Reuse

Borrowing it

Nothing to install: this file belongs to happier-dev/happier. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/happier-dev/happier/dev/.agents/skills/happier-diagnose/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/happier-dev/happier

Made for: Claude Code, Codex.

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 happier-diagnose

README.md
[![agentmods](https://agentmods.dev/badge/skills/happier-dev/happier/happier-diagnose.svg)](https://agentmods.dev/skills/happier-dev/happier/happier-diagnose)
Your own site
<a href="https://agentmods.dev/skills/happier-dev/happier/happier-diagnose"><img src="https://agentmods.dev/badge/skills/happier-dev/happier/happier-diagnose.svg" alt="Measured on agentmods" height="20"></a>
Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,611 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 5.1 $0.00090 $0.01611
Opus 5 $0.00045 $0.00805
Sonnet 5 $0.00018 $0.00322
Haiku 4.5 $0.00009 $0.00161

Measured yesterday against content hash 9c0f68b32820, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

happier-diagnose 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/skills/happier-diagnose/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Happier Diagnose

Investigate a Happier runtime/support incident from primary evidence, determine the originating cause when the evidence supports it, and report what is known, what is derived, and what remains unverified. Diagnosis is read-only: do not edit repository source or silently turn the investigation into a fix.

For a GitHub issue or coherent issue bundle, use .agents/skills/happier-issue-diagnose; it owns untrusted issue intake, private maintainer-evidence capability checks, version/release disposition, and the GitHub-facing report while composing this runtime evidence method when applicable. For a raw multi-issue corpus, use .agents/skills/happier-issue-triage first.

If the user requests a repository correction, finish the diagnosis or establish the deciding evidence, then use .agents/skills/happier-implement and its bug-fix loop. User-side recovery actions, private diagnostics upload, and public issue creation remain separate actions with their own authority.

1. Establish the observed incident

Inspect evidence already supplied or locally available before asking the user for more. Capture:

  • observed behavior and failure window;
  • expected behavior when it is established;
  • affected session, daemon, provider, server, account, host, and platform;
  • version/build/runtime identity;
  • what still works and the practical impact;
  • whether the user wants diagnosis only, local recovery guidance, or later reporting.

If no usable description or evidence exists, ask one concise question that requests the symptom and any Happier session ID or copied session metadata. Do not interrogate or ask for information that safe local/CLI inspection can retrieve.

Do not guess an expected result. Derive it from the user's stated expectation, a current product/external contract, or observed canonical behavior. If it remains materially unspecified, report that ambiguity rather than forcing a root-cause verdict.

2. Select the evidence path

Read runtime-evidence.md when session metadata, doctor/auth state, Happier logs, provider transcripts, connected-service homes, or installed-version source is needed. In the built-in /happier-diagnose prompt, use the bundled runtime-evidence reference included below.

Read the full file on GitHub · 118 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. yesterday Changed 9c0f68b32820
  2. 3d ago First seen · 118 lines · 90 tokens per session scan A 6705e4017200

Subscribe to this mod's changes

happier-diagnose is a skill published in the GitHub repository happier-dev/happier (1,624 stars, last pushed yesterday), licensed MIT. It adds 90 tokens to every session and 1,611 once invoked, about $0.0005 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 2026-09-03.

Related

Other skills, from other repositories