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.
npx skills add KevinZai/commander --skill ccc-adhdgit clone --depth 1 https://github.com/KevinZai/commanderWrote 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/kevinzai/commander/ccc-adhd)<a href="https://agentmods.dev/skills/kevinzai/commander/ccc-adhd"><img src="https://agentmods.dev/badge/skills/kevinzai/commander/ccc-adhd/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kevinzai/commander/ccc-adhd"><img src="https://agentmods.dev/badge/skills/kevinzai/commander/ccc-adhd.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00057 | $0.02215 |
| Opus 5.5 | $0.00023 | $0.00886 |
| Sonnet 5.5 | $0.00011 | $0.00443 |
| Haiku 4.5 | $0.00006 | $0.00221 |
Grade A, and why
ccc-adhd 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 today.
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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
$ccc-adhd — answer-first output mode
CC Commander · $ccc-adhd · every response leads with the answer, follows with the reasoning, and stops when the answer is done.
This reorders priority; it does not compress tokens. For fewer words, stack it with caveman mode (see "Stacking with caveman").
When to use / when not to
- Turn it on when the user keeps scrolling past preamble to find the command, in fast debugging loops, or when pairing with someone who needs "what do I run right now".
- Leave it off for architecture discussions, design reviews, or first-time walkthroughs where the reasoning is the deliverable.
What happens
1. Route the argument
$ARGUMENTS |
Action |
|---|---|
| empty | Read the state (step 2), report it in one line, then show the picker (step 3) |
on |
Write on (step 4), confirm in one line, apply the contract from the next sentence |
off |
Write off (step 4), confirm in one line, return to the normal shape immediately |
status |
Read and report the state (step 2); no picker, no write |
2. Read the state
The state file is <config dir>/commander/output-mode.json (~/.claude/commander/output-mode.json by default; the config dir is CCC_CONFIG_DIR, then CLAUDE_CONFIG_DIR, then ~/.claude). Until the lane has its own copy, read the ~/.claude/commander/ copy; writes go to the lane.
CCC_STATE="${CCC_CONFIG_DIR:-${CLAUDE_CONFIG_DIR:-$HOME/.claude}}/commander"; F="$CCC_STATE/output-mode.json"; [ -e "$F" ] || F="$HOME/.claude/commander/output-mode.json"
cat "$F" 2>/dev/null || echo '{}'
Report adhd (true/false) and stackCaveman. Default is OFF: a missing, empty or malformed file means normal Commander voice.
3. The picker (no argument)
Ask with AskUserQuestion (Codex: ask the same question in plain text):
question: "Answer-first output mode?"
header: "Output mode"
multiSelect: false
options:
- label: "🟢 Turn on"
description: "Every response leads with the fix; the answer is always the first line."
preview: "Writes {\"adhd\": true} to <config dir>/commander/output-mode.json"
- label: "🎯 On, stacked with caveman"
description: "Answer-first ordering and far fewer output words: reorder plus compress."
preview: "Writes {\"adhd\": true, \"stackCaveman\": true}"
- label: "Turn off"
description: "Back to the normal voice: context and reasoning first, answer woven in."
preview: "Writes {\"adhd\": false}"
- label: "Show the current setting"
description: "No change; read-only status check."
preview: "Reads <config dir>/commander/output-mode.json"
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.
- today Changed · -1 lines a0cfd9054182
- 2d ago Changed · +3 lines scan B → A 1932280bfc94
- 13d ago Changed · -3 lines · +2 tokens per session scan D → B 1f4be6b2a94a
- 1mo ago First seen · 146 lines · 55 tokens per session scan D 1bf08af4afee
ccc-adhd is a skill published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 2,215 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
memstack-automation-n8n-workflow-builder
Use this skill when the user says 'n8n workflow', 'build a workflow', 'automation workflow', 'connect services', or needs visual workflow design with node mapping, data transformations, and error handling for n8n. Do NOT use for standalone webhook endpoints or cron jobs.
memstack-automation-cron-scheduler
Use this skill when the user says 'cron job', 'scheduled task', 'run every', 'cron expression', 'recurring job', or needs production-grade scheduled jobs with overlap prevention, monitoring, and structured logging. Do NOT use for n8n workflows or event-driven webhooks.
search-first
A workflow rule for searching for an existing solution before writing new code. It checks the repository, internal mirrors, package registries, connected tools, and GitHub in that order.
debt-ops-init
Write or refresh a "Tech debt operations" section in the project's AGENTS.md so the team shares one source of truth for debt-ops disciplines. Run ONLY when the user explicitly asks to set up, install, or initialize debt-ops disciplines — never auto-invoke. Idempotent; only the managed section changes, other sections…
knowledgebase
Generate professional multi-page HTML knowledge bases and study guides for software engineering, data science, and AI/ML work — field guides, solution handbooks, service catalogs, team runbooks, onboarding documentation, and technical study resources. Produces self-contained, offline-capable HTML sites with sidebar…
debt-ops-metrics
Print a debt-ops health summary from the metrics log, covering registration rate, feedback action rate, ADR creation, and AI-authored share. Use when the user asks for "debt-ops metrics", "debt health", "registry stats", or a tech-debt health summary. Read-only, never writes the log.