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 cross-model-reviewgit 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/cross-model-review)<a href="https://agentmods.dev/skills/kalyvask/winning-writing/cross-model-review"><img src="https://agentmods.dev/badge/skills/kalyvask/winning-writing/cross-model-review/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/cross-model-review"><img src="https://agentmods.dev/badge/skills/kalyvask/winning-writing/cross-model-review.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 | $0.00132 | $0.01366 |
| Opus 5 | $0.00066 | $0.00683 |
| Sonnet 5 | $0.00026 | $0.00273 |
| Haiku 4.5 | $0.00013 | $0.00137 |
Grade A, and why
cross-model-review 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cross-model review
Source: points/named-failure-modes.md, points/banned-jargon.md, points/pre-send-checklist.md, points/cold-email-rules.md, points/ai-writing-rules.md. Read those first.
Why this exists
The model that drafted the email rationalizes its own choices. It picked the personalization, so the angle feels genuine. It used the word, so the word doesn't read as jargon. It made the claim, so the claim feels supported.
A second model — different weights, no investment in the draft — sees what the first model rationalized away. That's the whole point. If this skill runs on the same model that drafted, it adds nothing.
The contract
You are NOT here to make the email better. You are here to decide whether it ships.
Two verdicts only:
PASS— ship itFAIL— block, with the specific named failure modes listed
Borderline → fail. Cost of a block is one rewrite cycle. Cost of a templated email is the recipient's read of the sender forever.
Invocation rule
The orchestrator (coach.html, cold-email-coach, or the user) routes to a different model than the drafter. This skill assumes routing already happened.
If the user explicitly says you are the same model that drafted, output CANNOT REVIEW — same model as drafter and stop.
Required inputs
- The draft
- The recipient dossier (from
recipient-research) - The sender's
about-me.md - The original ask
If any are missing, output CANNOT REVIEW — missing [input] and stop. Do not guess.
The catalog of named failures
When you fail an email, name the mode in plain English so the sender knows what to rewrite, not just where they scored low. See points/named-failure-modes.md for the full catalog. Summary:
Strategy failures (5)
- Vague ask — not binary; "would love your thoughts," "any feedback"
- No "why now" — could have been sent a year ago
- Reaching across hierarchy without a reason — junior to senior, no bridge, no novel offer
- Stranger asking for a job — first contact asks for hire/intro instead of offering value
- Resume dump — multiple lanes instead of one specific story
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 · 127 lines · 132 tokens per session scan A 2c1af0e33a01
cross-model-review is a skill published in the GitHub repository kalyvask/winning-writing (14 stars, last pushed 6d ago), licensed MIT. It adds 132 tokens to every session and 1,366 once invoked, about $0.0007 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
oracle-grill-me
Grill the user relentlessly about a plan, decision, or idea, maintaining the project's domain model (CONTEXT.md, ADRs) as decisions crystallise. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
gauntlet
Empirically test whether a skill actually improves model output — before trusting it. Runs a controlled experiment: planted-flaw fixture, no-skill control arm, skill arm(s), optional cross-model arms via installed CLIs, blind judging with shuffled labels, and a pressure test for verdict stability. Produces…
review
Adversarially review a proposed or applied change to a training/evaluation pipeline: did the claimed mechanism actually engage, is the measurement still valid, what did it silently break. Use for /tml:review, "I made training faster, check it", "review this diff before I merge", "why did throughput improve but…
toolshed
Toolshed — durable, model-agnostic working state for ONE coding task (feature, investigation) as docs/work/SLUG/ under docs/, DELETED at close. Seeds STATE + decisions/questions/evidence with grades and reproduction commands. Use for "start a toolshed", "seed the task", "/toolshed start|resume|session-end|close", or…
shipkit-prompt-audit
Audit LLM prompt pipeline architecture — decomposition, parallelization, chain integrity, schema validation, fallback paths. Finds structural issues no linter catches.
oracle-domain-modelling
Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model.