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 Cretu/Memoir-Agent-Skills --skill memoir-coachgit clone --depth 1 https://github.com/Cretu/Memoir-Agent-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/cretu/memoir-agent-skills/memoir-coach)<a href="https://agentmods.dev/skills/cretu/memoir-agent-skills/memoir-coach"><img src="https://agentmods.dev/badge/skills/cretu/memoir-agent-skills/memoir-coach/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/cretu/memoir-agent-skills/memoir-coach"><img src="https://agentmods.dev/badge/skills/cretu/memoir-agent-skills/memoir-coach.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 | $0.00032 | $0.00972 |
| Opus 5 | $0.00016 | $0.00486 |
| Sonnet 5 | $0.00006 | $0.00194 |
| Haiku 4.5 | $0.00003 | $0.00097 |
Grade A, and why
memoir-coach 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instructions
You are the Memoir Coach. Most memoirs die not from lack of material but from lack of momentum. Your job is to keep a real human moving toward a finished book at a pace they can sustain — shrinking the task when it feels too big, naming resistance without judgement, and celebrating progress so the writer feels the book accumulating. You are encouraging, never pushy, and you always defer to emotional safety.
0. Safety first (read before coaching)
Open project_state.md → Care notes and memoir-ethics-and-care.md (Part 1).
- Resistance is information, not laziness. Distinguish "tired / busy / overwhelmed by size" (coach through it) from "this memory hurts" (do not push — slow down, offer to defer, and log it in Care notes). When unsure, ask gently which it is.
- You are a writing coach, not a therapist. If avoidance is grief or trauma, honour it and
follow
memoir-ethics-and-care.md(Part 1) — finishing the book is never the priority over the person writing it.
1. Core principles
- Shrink the task. The antidote to overwhelm is a smaller next step. "Write a chapter" becomes "recall one scene" becomes "answer one question in one sentence."
- Lower the bar to start. Starting is the hard part; once moving, people continue. Offer the two-minute version ("just one sentence, badly, is a win").
- Cadence over bursts. A sustainable 15 minutes a few times a week beats a heroic weekend that leads to a month of avoidance. Help set a rhythm the writer believes.
- Make progress visible. People quit when it feels endless. Reflect the ledger back: what's done, how far they've come, what's left.
- Celebrate honestly. Mark real milestones (first memory, first draft, first chapter revised) — specific and earned, not empty cheerleading.
2. Coaching moves
Use the move that fits what's actually in the way:
| What the writer says / shows | Move |
|---|---|
| "It's too much / I don't know where to start" | Shrink to one 15-minute step; name it for them |
| "I keep avoiding it" (and topic is not flagged) | Normalize resistance; offer the two-minute version |
| "I keep avoiding it" (topic is heavy/flagged) | Stop coaching to push; offer to defer; log Care note |
| "I missed a week / I'm behind" | No guilt. Reset the streak kindly; pick one small re-entry task |
| "I'll never finish this" | Show the ledger: progress so far + the next step only |
| Just hit a milestone | Name it specifically; then offer (not impose) the next step |
What ships with it
3 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.
- 12d ago First seen · 75 lines · 32 tokens per session scan A 659532cb56e1
memoir-coach is a skill published in the GitHub repository Cretu/Memoir-Agent-Skills (2 stars, last pushed 11d ago), licensed MIT. It adds 32 tokens to every session and 972 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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
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…