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 curiositech/some_claude_skills --skill checklist-disciplinegit clone --depth 1 https://github.com/curiositech/some_claude_skillsWrote 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/curiositech/some_claude_skills/checklist-discipline)<a href="https://agentmods.dev/skills/curiositech/some_claude_skills/checklist-discipline"><img src="https://agentmods.dev/badge/skills/curiositech/some_claude_skills/checklist-discipline/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/curiositech/some_claude_skills/checklist-discipline"><img src="https://agentmods.dev/badge/skills/curiositech/some_claude_skills/checklist-discipline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00047 | $0.03488 |
| Opus 5 | $0.00023 | $0.01744 |
| Sonnet 5 | $0.00009 | $0.00698 |
| Haiku 4.5 | $0.00005 | $0.00349 |
Grade A, and why
checklist-discipline 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 11d ago.
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 — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Checklist Discipline
Transform individual expertise into systematic excellence by catching inevitable cognitive failures and enabling team coordination in extreme complexity.
When to Use
✅ Use for:
- Complex processes with 100+ steps where memory/attention failures are inevitable
- High-stakes domains (surgery, aviation, construction, finance) where 1% error rates compound catastrophically
- Coordinating specialists across disciplines who must integrate decisions
- Converting strangers into functioning teams under time pressure
- Combating ineptitude (knowledge exists but isn't applied) vs. ignorance
❌ NOT for:
- Simple tasks with <10 steps that professionals reliably complete
- Teaching comprehensive procedures to complete novices (use training instead)
- Replacing professional judgment or handling true unpredictability
- Situations requiring detailed instruction manuals
- Avoiding responsibility through bureaucratic compliance theater
Core Process
Checklist Design Decision Tree
START: Define the complex process
│
├─> Is failure due to IGNORANCE (knowledge doesn't exist)?
│ └─> YES: Checklist cannot help → Research/develop knowledge first
│ └─> NO: Failure is INEPTITUDE (knowledge exists but misapplied) → CONTINUE
│
├─> Identify PAUSE POINTS (when to check)
│ ├─> Before critical commitment? (before anesthesia, takeoff, concrete pour)
│ ├─> Before point of no return? (before incision, before leaving OR)
│ ├─> After high-risk phase? (after landing, after patient leaves OR)
│ └─> Define 1-3 precise moments per process
│
├─> Choose FORMAT per pause point
│ ├─> Are users EXPERTS performing ROUTINE tasks?
│ │ └─> YES: DO-CONFIRM (perform from memory, then pause and verify)
│ └─> Are users NOVICES or tasks UNFAMILIAR?
│ └─> YES: READ-DO (execute each step as read, like recipe)
│
├─> Identify KILLER ITEMS (5-9 per pause point)
│ ├─> What's most dangerous if skipped?
│ ├─> What do experts reliably forget under stress?
│ ├─> What requires team coordination/shared awareness?
│ ├─> What has downstream cascading failures?
│ └─> OMIT: Steps professionals never skip, obvious items, comprehensive how-to
│
├─> Draft checklist
│ ├─> 5-9 items per pause point maximum
│ ├─> 60-90 seconds execution time maximum
│ ├─> One page, sans serif font, upper and lowercase
│ ├─> Precise, simple wording (no vagueness)
│ └─> Include forcing functions (verbal confirmations, sign-offs)
│
├─> TEST in real-world conditions
│ ├─> Use actual users, not designers
│ ├─> Observe in complex/stressful scenarios
│ ├─> Expect first draft to FAIL
│ ├─> Document: What was skipped? What took too long? What was confusing?
│ └─> ITERATE: Refine → Retest → Repeat until works consistently
│
└─> Implementation decision tree
├─> Make it TEAM CONVERSATION (not paperwork)
│ ├─> Require VERBAL confirmation
│ ├─> All team members state NAME and ROLE (activation phenomenon)
│ └─> Lowest-authority person initiates checklist
│
├─> Empower STOP authority
│ ├─> Anyone can halt process if checklist incomplete
│ └─> Create forcing function (e.g., metal tent until nurse approves)
│
└─> When to DEVIATE from checklist?
├─> Unique circumstances require professional judgment
├─> Time-critical emergency demands prioritization
└─> BUT: Deviation must be informed choice, not negligence
What ships with it
1 file 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.
- 11d ago First seen · 320 lines · 47 tokens per session scan A 59658dc820a2
checklist-discipline is a skill published in the GitHub repository curiositech/some_claude_skills (219 stars, last pushed 5d ago), licensed MIT. It adds 47 tokens to every session and 3,488 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…