i-have-adhd:A skill to stop your coding agent from burying the answer. ADHD-friendly output.

A skill to stop your coding agent from burying the answer. ADHD-friendly output.

Files	Last commit	Last update
.agents	Add Codex plugin compatibility	2 months ago
.claude-plugin	version bump to 0.2.0	25 days ago
.codex-plugin	version bump to 0.2.0	25 days ago
.cursor	fix: keep distributed skill metadata portable Synchronize the Cursor copy and use explicit string values with generic metadata keys so strict parsers can load either distribution.	1 month ago
.github	clarify always-on in claude code	10 days ago
.opencode	Address Copilot review: robust frontmatter strip + normal mode wording - opencode plugin: match hooks/always-on.mjs frontmatter regex (handles trailing whitespace on fences) and trailing-newline trim instead of trim() - mention "normal mode" alongside "stop adhd mode" in the always-on banner, command doc, and INSTALL OpenCode section	30 days ago
evals	docs: record the first run of the harness 14 cases, 3 trials, claude-opus-4-8, Claude Code 2.1.220. Weighted 4.045 -> 4.473; every dimension improves, including correctness (+0.190) and safety (+0.024). Blocking findings 7 -> 3. The release gate still fails, on "no blocking findings" -- absolute where the neighbouring rules are comparative, so more than halving the count is not enough. Two of the three remaining come from `agent-owned-edit`, which requires acting on a repository while every runner passes `--tools ""` and so cannot be passed by any run. Includes the caveats: three trials is few (per-case SD reaches 0.95), the judge shares a model family with the responses it grades, and 3 of 84 responses carry tool-call syntax as plain text. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>	1 month ago
extensions	fix: declare alwaysOn Pi config option	17 days ago
hooks	fix(hooks): raise SessionStart timeout to 30s The always-on launcher is capped at 5s, which measures Node's cold start under contention rather than the hook's own work. With several other SessionStart hooks registered, the launcher took 6549ms and was cancelled, so the ruleset was silently dropped from the session. The hook only does an existsSync, a readFileSync and a regex strip, with no network or blocking I/O, and it exits 0 immediately when the opt-in flag is absent. A wider ceiling cannot stall a session in practice, and 30s stays under Claude Code's 60s hook default.	24 days ago
scripts	Merge pull request #97 from Defaultuser361/eval-harness-judge-and-fidelity-fixes Make the eval harness runnable, then run it	10 days ago
skills	Merge pull request #104 from DaVinci42/fix-string-metadata fix: make skill metadata compatible with strict parsers	1 month ago
tests	Merge pull request #97 from Defaultuser361/eval-harness-judge-and-fidelity-fixes Make the eval harness runnable, then run it	10 days ago
.gitignore	Add reproducible skill quality evaluations 14 cases across direct answers, agent autonomy, debugging, explanations, destructive actions, ambiguity, progress, output contracts, planning, and medical boundaries. Weighted correctness/autonomy/actionability/ safety/concision rubric, baseline/candidate/comparator matrix, budget ceiling, blind scoring, resumability. Trimmed to the evaluation foundation; the repo-governance files from the original branch were split out. Groundwork for #4.	1 month ago
AGENTS.md	docs: define AI Agora comment routing	22 days ago
CONTRIBUTING.md	docs: clarify workflow labels	25 days ago
GEMINI.md	Add Gemini CLI support Two native routes: a self-contained custom command (opt-in, matches the skill's default posture) and an extension whose GEMINI.md imports the full skill for always-on. The command route's always-on subsection was folded into the extension route; the extension is the always-on path. README stays lean per repo policy.	1 month ago
INSTALL.md	clarify always-on in claude code	10 days ago
LICENSE	move to plugin mode, add logo	3 months ago
README.md	docs: align Thai README with current documentation	10 days ago
gemini-extension.json	version bump to 0.2.0	25 days ago
kimi.plugin.json	version bump to 0.2.0	25 days ago
logo.png	move to plugin mode, add logo	3 months ago
opencode.json	Add OpenCode support (server plugin + command + always-on) OpenCode was previously covered only by the generic agent-skills fallback (skill discovery, no command, no always-on). This adds a first-class OpenCode adapter mirroring the Codex/Pi layout: - .opencode/plugins/i-have-adhd.mjs: server plugin that registers the skills/ path and /i-have-adhd command, and appends the ruleset to the system prompt every turn when ~/.config/opencode/.i-have-adhd-always exists (the OpenCode equivalent of the SessionStart always-on hook). - .opencode/command/i-have-adhd.md: on-demand session command. - opencode.json: run-from-checkout entry point. - INSTALL.md: dedicated OpenCode section; dropped from the catch-all title. Ruleset stays sourced from skills/i-have-adhd/SKILL.md (frontmatter stripped at inject time) — no rule text duplicated.	30 days ago
package.json	version bump to 0.2.0	25 days ago
plugin.json	fix(antigravity): drop $schema pointing at a non-existent URL https://antigravity.google/schemas/v1/plugin.json returns 404 (the host is live; the path is not), and the Antigravity plugin docs describe plugin.json as a marker file with an optional name field — no schema is published. An editor that honours $schema fetches it, fails, and leaves the manifest unvalidated while looking authoritative. Drop the key until a real schema exists.	1 month ago
qwen-extension.json	version bump to 0.2.0	25 days ago

ADHD-friendly outputs. No ADHD diagnosis needed!

🇬🇧 · 🇨🇳 · 🇧🇷 · 🇯🇵 · 🇻🇳 · 🇰🇷 · 🇹🇭

Install

Copy/paste into your CLI prompt:

Install the i-have-adhd skill/plugin from https://github.com/ayghri/i-have-adhd, refer to the repo's AGENTS.md for instructions.

Or 🔗 check the installation instructions.

What it does

A skill for your coding assistant that stops it from burying the answer. Action first. Steps numbered. No "Hope this helps!"

What changes

Before

Great question! Let me think about this. Your auth flow has a few moving pieces: the middleware, the token verification, and the cookie handling. Looking at src/auth.ts, the verifyToken function (around lines 42-58) seems to be using an older jsonwebtoken API. One approach would be to update the package and rewrite that function. After making the change, you'd want to run the auth tests to confirm nothing breaks. By the way, you might also want to look at your dependency versions overall. Hope this helps! Let me know if you want to dig deeper.

After

Run npm install jsonwebtoken@latest, then edit src/auth.ts:42.

Open src/auth.ts

Replace verifyToken (lines 42–58) with the snippet below

Run npm test -- auth.spec.ts

Next: paste the first failing line if any test fails.

The rules

10 rules. Full text in SKILL.md.

Lead with the next action.
Number multi-step tasks.
End with one concrete next step.
Suppress tangents.
Restate state every turn.
Specific time estimates (minutes, not "a bit").
Make wins visible.
Matter-of-fact errors.
Cap lists at 5 items.
No preamble. No recap. No closers.

Tune it

Fork, edit skills/i-have-adhd/SKILL.md, then swap your copy in:

claude plugin uninstall i-have-adhd            # drop the upstream copy first:
claude plugin marketplace remove i-have-adhd   # fork and upstream share both names
claude plugin marketplace add <your-username>/i-have-adhd
claude plugin install i-have-adhd@i-have-adhd

Restart Claude Code, then re-invoke /i-have-adhd.

Credits

Loosely based on The Adult ADHD Tool Kit by J. Russell Ramsay and Anthony L. Rostain. Adapted for how an LLM should respond, not how a human should organize their day.

License

MIT.

Star ⭐ if it saved you one scroll past one "Great question!"

Introduction

Claude 代码技能，防止答案被隐藏。适合 ADHD 用户的输出。【此简介由AI生成】

MIT Python 192Commitsadhd claude-claude-code-plugin claude-skills developer-tools productivity

Customize your domain

README

14443.13 K2.45 KVisit GitHub