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 cataloggit 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/catalog)<a href="https://agentmods.dev/skills/kalyvask/winning-writing/catalog"><img src="https://agentmods.dev/badge/skills/kalyvask/winning-writing/catalog/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/catalog"><img src="https://agentmods.dev/badge/skills/kalyvask/winning-writing/catalog.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00114 | $0.01982 |
| Opus 5 | $0.00057 | $0.00991 |
| Sonnet 5 | $0.00023 | $0.00396 |
| Haiku 4.5 | $0.00011 | $0.00198 |
Grade A, and why
winning-writing 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 9d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Winning Writing — mode-aware
Source: Rachel Konrad's GSB guest lectures, Heidi Roizen's rules, 25 model letters, live student critiques. Rule library is in rules/catalog.json; mode definitions in rules/modes.json. Full playbook in references/cold_outreach_playbook.md.
Invocation
/winning-writing <mode> "paste draft here"
Where <mode> is one of: cold-email, memo, essay, profile, readme, linkedin-post, or default.
If no mode is given, defaults to default (every rule in the catalog fires). The mode arg filters the catalog to rules tagged with that mode, applies any per-mode severity overrides from modes.json, and applies the mode's target-length check if one is set.
What this skill does on every invocation
- Read
rules/modes.jsonto get the active mode's definition (label, description, target length, severity overrides). - Read
rules/catalog.jsonand filter to rules whosemodesarray includes the active mode (or the active mode isdefault). - Apply per-mode severity overrides to the filtered rules.
- Critique the draft against the filtered list. For each rule, name the rule, quote the failing span, give the suggested rewrite, and cite the rule id so the user can look it up.
- Apply the length check if the active mode declares a
target_wordsvalue. - Return a structured critique with critical issues first, then issues, then warns. End with a clean rewrite of the draft.
Output format (unchanged from prior versions)
## Mode
<mode label> — <one-sentence mode description>
## Flags
### Critical
- <rule id>: <one-sentence why this fires> ("<quoted span>")
Suggested: "<rewrite>"
### Issue
...
### Warn
...
## Length
<word count> / <target> [if mode has target_words]
## Rewrite
<full clean rewrite>
## What changed (3 bullets)
- ...
If no flags fire, say so explicitly: "No flags from the catalog. The draft is clean against the rules; verify the substance separately."
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.
- 9d ago First seen · 135 lines · 114 tokens per session scan A cd3f8b333bc5
winning-writing is a skill published in the GitHub repository kalyvask/winning-writing (13 stars, last pushed 3d ago), licensed MIT. It adds 114 tokens to every session and 1,982 once invoked, about $0.0006 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.
version-comparator
Compares two versions of an article and produces a structured change report — highlighting substantive edits, additions, deletions, and tone shifts — so the editor or writer can quickly understand what changed and assess whether the revisions improved the piece.
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.