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 MereWhiplash/engram-cogitator --skill sketchinggit clone --depth 1 https://github.com/MereWhiplash/engram-cogitatorWrote 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/merewhiplash/engram-cogitator/sketching)<a href="https://agentmods.dev/skills/merewhiplash/engram-cogitator/sketching"><img src="https://agentmods.dev/badge/skills/merewhiplash/engram-cogitator/sketching/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/merewhiplash/engram-cogitator/sketching"><img src="https://agentmods.dev/badge/skills/merewhiplash/engram-cogitator/sketching.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 | $0.00038 | $0.00723 |
| Opus 5 | $0.00019 | $0.00362 |
| Sonnet 5 | $0.00008 | $0.00145 |
| Haiku 4.5 | $0.00004 | $0.00072 |
Grade A, and why
sketching 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 12d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sketching
The MEDIUM path: all of the discipline of the full flow, a fraction of the ceremony. One half-page combo doc replaces the design doc + plan pair; the execution rigor (TDD, verification, inline review) is identical.
Announce: "I'm using the sketching skill — MEDIUM-sized work, combo doc instead of full design + plan."
When This Fits
New behavior that is contained: one component, reversible-ish, no
architecture/data-model/API-surface change. Too big for straight @tdd
(there are real decisions to record), too small for brainstorming →
writing-plans (two ceremony docs would outweigh the change).
The Flow
Quick Recon → Combo Doc → One Confirmation → Execute (TDD) → Persist
Step 1: Quick Recon
Lightweight — not the full brainstorming recon:
ec_search:
query: [feature area]
If graphify is enabled in .cogitation/config.json, one structural query on
the touched area. Skip anything that doesn't sharpen the sketch.
Step 2: The Combo Doc
Write docs/sketches/YYYY-MM-DD-<topic>.md, capped at half-page:
# <Topic>
**What/Why:** 2–3 sentences — the change and what it buys.
**Approach:** the chosen approach, and the alternative rejected (one line on why).
**Risks/Edges:** failure modes, empty/error states worth guarding.
## Tasks
- [ ] 1. <first task — becomes a failing test>
- [ ] 2. <...2–5 items total, dependency order>
The task checklist doubles as the plan — tick items off as they complete, so a dead session can resume from the doc.
Step 3: One Confirmation Round
Show the combo doc; get one confirmation from the user. This is a sanity check, not an interview — no question loop. Fold in corrections and go.
Step 4: Execute Continuously
Every task follows @tdd (red → green → refactor), with @verifying
before claiming completion and Tier 0 inline self-review at the end — the same
discipline as executing-plans, none of its ceremony. Commit per task; tick
the checklist as you go.
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.
- 12d ago First seen · 93 lines · 38 tokens per session scan A eef4b0ee7af4
sketching is a skill published in the GitHub repository MereWhiplash/engram-cogitator (4 stars, last pushed 2mo ago), licensed MIT. It adds 38 tokens to every session and 723 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 2026-08-31.
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…