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 mlopscommunity/Coding-Agents-Conference-skills --skill crispi-planninggit clone --depth 1 https://github.com/mlopscommunity/Coding-Agents-Conference-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/mlopscommunity/coding-agents-conference-skills/crispi-planning)<a href="https://agentmods.dev/skills/mlopscommunity/coding-agents-conference-skills/crispi-planning"><img src="https://agentmods.dev/badge/skills/mlopscommunity/coding-agents-conference-skills/crispi-planning/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/mlopscommunity/coding-agents-conference-skills/crispi-planning"><img src="https://agentmods.dev/badge/skills/mlopscommunity/coding-agents-conference-skills/crispi-planning.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 | $0.00036 | $0.02553 |
| Opus 5 | $0.00018 | $0.01277 |
| Sonnet 5 | $0.00007 | $0.00511 |
| Haiku 4.5 | $0.00004 | $0.00255 |
Grade A, and why
crispi-planning 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 10d 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 — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CRISPI Planning
Overview
A multi-stage planning pipeline that separates research, design, and implementation into distinct context windows. Each stage produces a written artifact that feeds the next, preventing context window pollution and ensuring alignment before code is written.
CRISPI stands for: Context, Research, Implementation design, Structured plan, Implementation.
Core principle: Don't use prompts for control flow -- use actual control flow. Each stage runs in a fresh context window with fewer than 40 instructions, producing a document that becomes the input for the next stage.
When to Use
- Before starting any feature, bug fix, or refactor that touches more than one file
- When a ticket is ambiguous and needs research before you can estimate scope
- When you need alignment with stakeholders before writing code
- When working on unfamiliar parts of the codebase
- When a previous attempt failed due to context window exhaustion
When NOT to Use
- One-line fixes or typo corrections
- Changes where the implementation is already obvious and self-contained
- Purely mechanical refactors (rename a variable, update an import path)
- When you are already inside an implementation stage with a validated plan
Common Mistakes
| Mistake | Why it's wrong |
|---|---|
| Combining research and implementation in one context window | Research context pollutes implementation. Separate them so the agent doing research doesn't anchor on a specific solution, and the agent writing code doesn't waste tokens on exploration. (Dex [05:44:35]) |
| Writing a plan that reads like a horizontal layer cake ("first do all the models, then all the routes, then all the tests") | Horizontal plans break at integration boundaries. Build vertically -- one working slice at a time, each independently testable. (Dex [05:58:16]) |
| Skipping the plan and jumping straight to code | "Always start with a plan before coding." The plan is both your roadmap and your recovery mechanism when the context window resets. (Rafael [03:16:14], Sid [00:34:14]) |
| Writing the plan only in your head or in plan mode UI | Write plans to a file (docs/plan.md or docs/plans/). Files persist across context windows; plan mode state does not. (Rob [03:29:27], Sid [00:41:44]) |
| Letting the plan go stale during implementation | Keep the plan file updated with current task status -- check off completed items, note deviations. It is your context recovery mechanism. (Josh [03:28:11]) |
| Asking the research agent leading questions that reveal your preferred solution | Hide intent from research context. Frame as neutral questions so the agent explores broadly rather than confirming your bias. (Dex [05:44:35]) |
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.
- 10d ago First seen · 228 lines · 36 tokens per session scan A 5f4683cd381e
crispi-planning is a skill published in the GitHub repository mlopscommunity/Coding-Agents-Conference-skills (37 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 36 tokens to every session and 2,553 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…