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.
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.
curl -O https://raw.githubusercontent.com/happier-dev/happier/dev/.agents/skills/happier-diagnose/SKILL.mdgit clone --depth 1 https://github.com/happier-dev/happierWrote 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.
[](https://agentmods.dev/skills/happier-dev/happier/happier-diagnose)<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>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.
| Model | Per session | Once 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 |
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.
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.
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.
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.
- yesterday Changed 9c0f68b32820
- 3d ago First seen · 118 lines · 90 tokens per session scan A 6705e4017200
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.
Other skills, from other repositories
debug-visualization
Use when creating any game or interactive toy, when adding gameplay/UI features to one, when the builder asks for value tweaks in any language (too fast/slow, too big/small, a bit more/less, move it left/right/up/down, can't hit it, my tap doesn't register, hitbox, feels floaty/heavy/off, easier/harder, change X from…
code_explorer
Explores the repository to locate primary source files, coupled UI components, and test files for bug reports or feature requests.
audit
Run technical quality checks across accessibility, performance, theming, responsive design, and anti-patterns. Generates a scored report with P0-P3 severity ratings and actionable plan. Use when the user wants an accessibility check, performance audit, or technical quality review.
social-physics-filter
Unified boundary enforcement, interpersonal diagnostic, and relational audit engine. Absorbs 40 psychology + 2 social protocols and all relationship case studies.
therapeutic-ifs
Unified inner work engine: Schema deconstruction (diagnosis) + IFS therapy (treatment). Absorbs: schema-deconstruction.
Diagnostic-First Refactoring
A non-destructive, decoupled analysis protocol for refactoring code. Generates a "Bill of Materials" report before any code is touched.