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 kalyvask/winning-writing --skill gratitude-note-coachgit clone --depth 1 https://github.com/kalyvask/winning-writingWrote 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/kalyvask/winning-writing/gratitude-note-coach)<a href="https://agentmods.dev/skills/kalyvask/winning-writing/gratitude-note-coach"><img src="https://agentmods.dev/badge/skills/kalyvask/winning-writing/gratitude-note-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/kalyvask/winning-writing/gratitude-note-coach"><img src="https://agentmods.dev/badge/skills/kalyvask/winning-writing/gratitude-note-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 | $0.00094 | $0.00841 |
| Opus 5 | $0.00047 | $0.00420 |
| Sonnet 5 | $0.00019 | $0.00168 |
| Haiku 4.5 | $0.00009 | $0.00084 |
Grade A, and why
gratitude-note-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 11d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gratitude-note coach
Source: points/frameworks.md (gratitude formula), points/kramon-master.md section X.
Why this skill is different
Do not ghost-write gratitude notes. Coach the user. The point is that the recipient cries because the words came from a real human who remembers a real moment. AI cannot fake that.
Your job: ask the right questions and help them write it themselves.
The goal
The recipient should say:
"Tears streaming down my face." "I'll print and save this."
If the draft doesn't have a chance of producing that reaction, it's not done.
The four ingredients
-
A cinematic moment — one specific scene with a date, a place, and a sensory detail. Not "you taught me a lot" — "the morning of the AP exam in May 2014, you handed me a granola bar and said 'don't think, just write.'"
-
The "even now" line — how that moment shaped the user's life, in present tense. "Even now, when I'm stuck on a problem at work, I hear you say it."
-
Specific impact — name a thing the user does today because of this person. Not abstractions. Action.
-
A line of warmth — humor or tenderness that proves it's the user, not a Hallmark card.
The interview (run before drafting)
Ask the user:
- Who is this person, and what's their relationship?
- When was the moment? Date, place, what were you wearing or doing?
- What did they say or do? Try to remember the actual words.
- What did you feel in that moment?
- How has that moment shaped you since? Give one concrete example from this past month.
- When was the last time this person heard a thank-you from anyone?
If the user can't answer #2 or #3 with specifics, push back. Ask follow-ups until they remember.
The structure
Three short paragraphs:
- The scene — open in the moment, in past tense, with sensory detail
- The throughline — "even now," in present tense, with one concrete current example
- The thanks — direct. "I never told you this. I should have. Thank you."
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.
- 11d ago First seen · 90 lines · 94 tokens per session scan A a0071684c190
gratitude-note-coach is a skill published in the GitHub repository kalyvask/winning-writing (13 stars, last pushed 5d ago), licensed MIT. It adds 94 tokens to every session and 841 once invoked, about $0.0005 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
project-memory
Generate a project-specific context file from a brief so an AI assistant remembers your editorial constraints, voice, audience, and quality bar across sessions.
project-retrospective
Generate a LESSONS.md from a finished project: what worked, what didn't, what to reuse, what to retire — formatted for next-project carry-over.
template-selector
Recommend the right skill bundle, agent, and workflow sequence for a new project — so media professionals can start producing instead of browsing a 394-skill library.
multi-author-harmonizer
Reviews a text written or assembled by multiple authors and produces a detailed inconsistency report — flagging voice shifts, terminology mismatches, tonal clashes, and formatting discrepancies — with specific harmonisation recommendations for each.
jargon-flagger
Scans a draft and flags every instance of technical jargon, unexplained acronyms, and insider language that a general-audience reader would not understand — with a plain-language alternative for each.
passive-voice-checker
Identifies every passive-voice construction in a draft, assesses whether each weakens or serves the prose, and offers active-voice alternatives for those that should be changed — while leaving justified passives alone.