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/kodingdev/meridian/sketchnpx skills add KodingDev/meridian --skill sketchgit clone --depth 1 https://github.com/KodingDev/meridianWhat 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 | $0.00015 | $0.01006 |
| Opus 5 | $0.00008 | $0.00503 |
| Sonnet 5 | $0.00003 | $0.00201 |
| Haiku 4.5 | $0.00002 | $0.00101 |
Grade A, and why
sketch 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 yesterday.
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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sketch
A lightweight spec for small fixes.
When to Use
Use only when the user invokes it. Unfamiliar external APIs alone are not a disqualifier; they trigger meridian:research at step 2.
Process
-
Targeted context. Locate and read the file(s) the Plan will modify — typically 1-2. Read-only references (types, callers) don't count toward the 3-file ceiling. If more than 3 files will be modified, escape to
brainstorm.Also consult the auto-memory system (
MEMORY.mdis already in context). Read anyfeedbackorusermemories that apply to this fix; persistent rules ("test before claiming done", "no AI slop comments", "always use existing utils") get pre-populated into User Constraints rather than waiting for the user to restate them. If a memory is stale relative to the code, trust the code and update or remove the memory. -
Identify research needs. "Unfamiliar" means: imports a library not in the immediate file, or uses an API not verified in this session. If unfamiliar, invoke
meridian:research. After it returns, re-evaluate scope: if research surfaced unexpected complexity, escape tobrainstorm; otherwise resume. -
Clarify if needed. Use the host's structured question tool for genuine ambiguity, or ask in plain text and wait when that tool is unavailable. This includes proposing a slug if
/meridian:sketchwas invoked with no description. Capture stated constraints (do/don'trules) for the User Constraints section. Skip if the request is unambiguous. -
Write the sketch file. Path:
.meridian/sketches/YYYY-MM-DD-<slug>.md(date in local time). Slug: lowercase, ASCII-fold, replace non-alphanumerics with hyphens, collapse, trim, truncate to 60 chars, re-trim. If the result is empty, propose a slug at step 3. On filename collision, append-2,-3. Create the directory if missing. Do NOT commit. Do NOT stage.
What ships with it
2 files 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.
- yesterday First seen · 52 lines · 15 tokens per session scan A bd97ccf8124a
sketch is a skill published in the GitHub repository KodingDev/meridian (5 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 1,006 once invoked, about $0.0001 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 2026-08-31.
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…