OpenCode + I Have ADHD Skill: Fix Coding Agent Output, Less Tokens, Faster Answers
This video explains the 'I Have ADHD' skill, a single MIT-licensed markdown file with over 18,000 GitHub stars that forces coding agents to lead with the action, cut preambles and closing pleasantries, and restate progress every turn, then installs and demos it in OpenCode building a small expense tracker.
AI Stack Engineer9 minTranscript found
Quick learning frame
Read this before watching.
Coding-agent workflow is the loop of inspect, route, plan, edit, verify, summarize, and decide what should be automated next.
New playlist item from AI Stack Engineer; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Skill you build: The ability to install and tune a single-file agent skill that rewrites a coding assistant's output rules (lead with the action, number steps, restate progress, cut filler) so long agent sessions stay easy to track.
Watch for the shift from claim to mechanism. The learning value is the point where the transcript reveals a repeatable action, tool boundary, context move, review habit, or artifact.
Concept diagram
Where this video fits.
01Inspect context
02Route tool
03Plan work
04Edit safely
05Verify behavior
06Report next step
Deep lesson
Turn this video into working knowledge.
1,563 cleaned transcript words reviewed across 472 timed caption segments.
Thesis
OpenCode + I Have ADHD Skill: Fix Coding Agent Output, Less Tokens, Faster Answers teaches a practical coding-agent workflow move: This video explains the 'I Have ADHD' skill, a single MIT-licensed markdown file with over 18,000 GitHub stars that forces coding agents to lead with the action, cut preambles and closing pleasantries, and restate progress every turn, then installs and demos it in OpenCode building a small expense tracker.
The goal is not to remember the video. The goal is to extract the operating principle, tie it to timestamped evidence, test how far the claim transfers, and make something reusable.
0:00
Action first, filler gone
“Every AI coding agent has the same annoying habit. You ask a small question and you get back three paragraphs before the answer shows up. There's a warm opener, a short lecture on why the topic is complicated,...”
The skill's name describes an output format, not a diagnosis: it forces the model to put the command, file, or line to open first and cut the warm opener, unrequested suggestions, and 'hope this helps' sign-off, so the before/after example carries the same information in roughly a quarter of the reading. Take a recent verbose AI answer you received and rewrite it using only the action-first line plus numbered steps, then compare word counts.
5:28
Ten rules from five brain facts
“Codex, you trigger it with a dollar sign instead of a slash. The repo also ships a cursor folder, a Gemini extension JSON file, and an agents plugins folder, so Cursor and Gemini CLI are covered, too. Different...”
The skill.md file derives 10 rules from five facts about how attention works (small working memory, starting is hardest, vague time estimates all feel the same, progress must be visible): lead with the next action, number steps with one bounded action each, end every response with a sub-two-minute next step, kill tangents, restate where you are every turn, give real time estimates in minutes, make finished work visible and runnable, ban vague error language in favor of naming cause and fix, cap lists at five items, and remove preambles and closing pleasantries. Pick three of the 10 rules that would fix your biggest annoyance with a coding agent's output and check whether your current agent already follows them.
6:04
When brevity should lose
“Claude {slash} skills in the same repo, walking up until it hits the get work tree. Globally, it checks the config folder under open code, plus your home {dot} Claude skills folder. So, a skill written for Claude...”
The skill has a 'when to break the rules' section: it explains fully if you explicitly ask to be walked through something, confirms before destructive actions like a force push or schema migration since safety beats brevity, stops and names an assumption if you've been stuck three turns in a row, asks a short clarifying question if your request is unclear, and gives ranked options with tradeoffs instead of forcing one path when you ask for options. Write down one destructive action in your own workflow (a migration, a force push, a delete) and confirm your agent still pauses to confirm even with this skill installed.
01
Inspect context
Start with this video's job: This video explains the 'I Have ADHD' skill, a single MIT-licensed markdown file with over 18,000 GitHub stars that forces coding agents to lead with the action, cut preambles and closing pleasantries, and restate progress every turn, then installs and demos it in OpenCode building a small expense tracker. Treat "Inspect context" as the outcome you are trying to make visible, not a topic label. Anchor it to 0:00, where the video says: “Every AI coding agent has the same annoying habit. You ask a small question and you get back three paragraphs before the answer shows up. There's a warm opener, a short lecture on why the topic is complicated,...”
02
Route tool
Use "Route tool" to locate the part of the coding-agent workflow mechanism the video is demonstrating. Ask what changes in your real setup if this claim is true. Anchor it to 5:28, where the video says: “Codex, you trigger it with a dollar sign instead of a slash. The repo also ships a cursor folder, a Gemini extension JSON file, and an agents plugins folder, so Cursor and Gemini CLI are covered, too. Different...”
03
Plan work
Turn "Plan work" into the reusable artifact for this lesson: A coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal. This is where watching becomes something you can inspect and reuse.
04
Edit safely
Use "Edit safely" as the application surface. Decide whether the idea touches a browser flow, a local file, a model choice, a source document, a UI, or a review step.
05
Verify behavior
Use "Verify behavior" to prove the lesson. The evidence should connect back to the video title, transcript anchors, and a concrete output, not a generic best-practice claim.
06
Report next step
Use "Report next step" to carry the idea forward: save the prompt, checklist, diagram, or operating rule that would make the next agent run better.
Example
Source-backed artifact packet
Convert the video into a scoped artifact request that includes the transcript claim, mechanism, acceptance criteria, and proof. The output should be a coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal..
Example
Coding-agent workflow proof brief
Separate what the speaker claims, what the demo actually proves, and what still needs outside verification before you adopt the coding-agent workflow pattern.
Example
Teach-back module
Transform the lesson into a definition, a Inspect context -> Route tool -> Plan work -> Edit safely -> Verify behavior -> Report next step diagram, one misconception, one practice exercise, and a check-for-understanding question.
Do not learn it wrong
Treating the title as the lesson without checking what the transcript actually says.
choosing tools by hype
losing context across agents
letting parallel sessions become invisible
Letting the lesson drift into generic Codex vs Claude comparison.
Letting the lesson drift into feature lists without task routing.
Letting the lesson drift into claims that ignore limits or recovery.
Do not count this as learned until these are true.
01
State the transcript-backed claim in your own words: This video explains the 'I Have ADHD' skill, a single MIT-licensed markdown file with over 18,000 GitHub stars that forces coding agents to lead with the action, cut preambles and closing pleasantries, and restate progress every turn, then installs and demos it in OpenCode building a small expense tracker.
02
Explain the practical stakes without hype: New playlist item from AI Stack Engineer; queued for transcript-backed review, topic mapping, and a practical learning artifact.
03
Map the idea onto the Intent -> Context -> Generation surface -> Preview -> Critique -> Implementation handoff sequence and name the weakest link.
04
Produce the artifact and include the evidence that proves it: A UI control-surface critique sheet with context inputs, artifact visibility, review criteria, and implementation handoff.
Put it into practice
Give this grounded prompt to Codex or Claude after watching.
You are helping me turn one specific YouTube video into real, durable learning.
Source video:
- Title: OpenCode + I Have ADHD Skill: Fix Coding Agent Output, Less Tokens, Faster Answers
- URL: https://www.youtube.com/watch?v=Wu_Vos03Uxg
- Topic: Interfaces + Open Design
- My current learning frame: Install the I Have ADHD skill in whichever coding agent you use daily, ask it to build one small real feature, and compare how it restates progress and handles a build error against how your agent behaved before.
- Why this matters: New playlist item from AI Stack Engineer; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Transcript anchors from this exact video:
- 0:00 / Evidence 1: "Every AI coding agent has the same annoying habit. You ask a small question and you get back three paragraphs before the answer shows up. There's a warm opener, a short lecture on why the topic is complicated,..."
- 3:06 / Evidence 2: "caps lists at five items and rule 10 removes preambles, recaps, and closing pleasantries entirely. There's a section most people skip called when to break the rules and honestly, it's the reason this thing works instead of being..."
- 5:28 / Evidence 3: "Codex, you trigger it with a dollar sign instead of a slash. The repo also ships a cursor folder, a Gemini extension JSON file, and an agents plugins folder, so Cursor and Gemini CLI are covered, too. Different..."
- 6:04 / Evidence 4: "Claude {slash} skills in the same repo, walking up until it hits the get work tree. Globally, it checks the config folder under open code, plus your home {dot} Claude skills folder. So, a skill written for Claude..."
- 7:39 / Evidence 5: "page, add an item, and refresh. The thing I didn't expect is how much this matters in long sessions. When you're 30 or 40 messages into an agent run, the biggest problem isn't code quality. It's that you..."
Video-aware target:
- Prompt lane: Coding-agent workflow
- Mechanism to extract: Find the workflow rule that explains when and how to use Codex, Claude Code, browser control, dashboards, or manual review.
- Artifact to produce: A coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal.
- Artifact must include: task class; agent/tool choice; context packet; verification step; handoff/recovery rule
Your task:
1. Use the transcript anchors above as the primary source packet. If you add outside context, label it clearly as outside context and keep it secondary.
2. Create a source-check table with columns: timestamp, claim, transcript support, what the demo proves, confidence, and what still needs verification.
3. Extract the actual teachable mechanism from the video: Find the workflow rule that explains when and how to use Codex, Claude Code, browser control, dashboards, or manual review. Do not invent claims that are not supported by the title, lesson frame, or transcript anchors.
4. Build a reusable learning artifact: A coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal.
5. Include:
- a plain-English definition of the core idea
- a diagram or structured model using this sequence: Inspect context -> Route tool -> Plan work -> Edit safely -> Verify behavior -> Report next step
- answers to these source questions: What workflow pain is being solved? | What exact coordination mechanism is shown? | What evidence proves it changes the work?
- 3 concrete examples that apply the video idea to real agentic work, such as rate-limit routing; browser verification after a UI edit; long-running /goal session review
- 2 failure modes the video helps prevent, chosen from the transcript evidence and these likely risks: choosing tools by hype; losing context across agents; letting parallel sessions become invisible
- a checklist for the next real workflow, focused on: routing decision, context portability, verification, handoff summary
- one practical exercise with a clear done signal: Route three recent tasks across Codex, Claude, browser checks, and manual review with a reason for each.
6. Add a "learning transfer" section: what changes in my workflow tomorrow if I actually learned this?
7. Add a "source check" section that cites which transcript anchor supports each major takeaway.
Quality bar:
- Make this specific to "OpenCode + I Have ADHD Skill: Fix Coding Agent Output, Less Tokens, Faster Answers", not a generic Interfaces + Open Design essay.
- Each workflow rule must point to a timestamped claim or demo moment, then state what remains unproven.
- Prefer operational examples, failure modes, and reusable artifacts over broad definitions.
- Call out uncertainty instead of smoothing over weak evidence.
- Avoid these generic drifts: generic Codex vs Claude comparison; feature lists without task routing; claims that ignore limits or recovery.
- If evidence is weak or missing, stop and say what transcript segment or timestamp needs review instead of guessing.
- Finish with a concise artifact I could paste into my learning app.
Misconceptions
What to stop believing.
A beautiful page is automatically a good learning tool.
Learning requires sequence, active recall, feedback, and application.
Generated UI should be accepted as-is.
Generated UI needs critique, revision, and browser verification.
Practice studio
Learning only counts when you make something.
01
Transcript evidence map
Separate what the video actually says from what you already believe about the topic.
3 source-backed takeaways with timestamps, confidence, and a transfer note.02
One useful artifact
Apply the video to a real workflow and produce a coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal..
A reusable artifact with a done signal and one verification step.03
Coding-agent workflow teach-back card
Explain the coding-agent workflow mechanism to someone who has not watched the video yet.
A 90-second explanation, one diagram, one example, and one misconception to avoid.
Recall check
Answer first, then reveal — without rewatching.
What does the 'I Have ADHD' skill's name actually refer to, and what does it change about agent output?
What five facts about how an ADHD brain reads drive the skill's 10 output rules?
According to the 'when to break the rules' section, when should the skill let the agent take a longer, less brief response?
Source shelf
Use the video as a doorway, then verify with primary sources.
