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 agentmods add skills/rakovi4/continue-framework/plainnpx skills add rakovi4/continue-framework --skill plaingit clone --depth 1 https://github.com/rakovi4/continue-frameworkWhat 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 | $0.00062 | $0.00643 |
| Opus 5 | $0.00031 | $0.00321 |
| Sonnet 5 | $0.00012 | $0.00129 |
| Haiku 4.5 | $0.00006 | $0.00064 |
Grade A, and why
plain 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 2d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/plain - Explain It In Plain Words
The user pressed this because the last explanation didn't land. Re-explain the same thing — plainly.
The one rule: think hard, explain plain
This skill changes HOW you say the answer. It does NOT change the work.
- Reasoning, analysis, code, commit messages, test descriptions, ADRs, specs: stay exactly as rigorous and technical as always. Untouched.
- Only the user-facing explanation gets simplified.
The simplification is a translation step at the very end — never a constraint on the thinking that produced the answer. Do not "dumb down" your analysis to make the explanation easier. Do the hard thinking in full, then translate the result.
How to explain plain
- Lead with the one fact the whole thing hinges on. Find the single load- bearing idea and say it first, in one sentence. Everything else hangs off it.
- Use ordinary words for the real thing. Say what it actually is, in words a non-expert already knows. If a technical term is unavoidable, say the plain version first and attach the term once, in parentheses.
- No analogies. Don't reach for a recipe, a factory, a filing cabinet, a traffic light. An analogy swaps the real thing for a different thing and leaves the user to map it back — that is extra work, not less, and it reads as talking down to someone who knows their own domain. Explain the actual thing plainly instead. This is the most common failure of this skill.
- Short sentences. One idea each. Cut clauses that don't carry weight.
- Drop the hedging. No "it depends", no stacked qualifiers, no defensive "well, technically". Say the thing.
- Sound like a person, not a filled-in template. Plain prose is usually right. Don't open every answer with a bolded thesis line, don't bold a phrase in every bullet, don't force a list where two sentences would do, and don't close by restating what you just said. Vary the shape to fit the answer.
- Stop when it lands. Don't append a second, more technical version "for completeness" — that undoes the point. If they want depth, they'll ask.
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.
- 2d ago First seen · 51 lines · 62 tokens per session scan A e1cd460865a0
plain is a skill published in the GitHub repository rakovi4/continue-framework (50 stars, last pushed 5d ago), licensed MIT. It adds 62 tokens to every session and 643 once invoked, about $0.0003 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.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…