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.
git clone --depth 1 https://github.com/MohtashamMurshid/md-to-docxWrote 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/rules/mohtashammurshid/md-to-docx/releases)<a href="https://agentmods.dev/rules/mohtashammurshid/md-to-docx/releases"><img src="https://agentmods.dev/badge/rules/mohtashammurshid/md-to-docx/releases/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/rules/mohtashammurshid/md-to-docx/releases"><img src="https://agentmods.dev/badge/rules/mohtashammurshid/md-to-docx/releases.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 | $0.00012 | $0.00565 |
| Opus 5 | $0.00006 | $0.00282 |
| Sonnet 5 | $0.00002 | $0.00113 |
| Haiku 4.5 | $0.00001 | $0.00056 |
Grade A, and why
releases 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Releases
This repo uses semantic-release on push to main. The agent MUST NOT do any of these manually:
- Bump
versioninpackage.json/package-lock.json - Edit
CHANGELOG.md(other than historical entries that already exist) - Create git tags (
git tag v*) - Create GitHub Releases (
gh release create) - Run
npm publish
All of the above happen automatically from .github/workflows/release.yml driven by .releaserc.json.
Commit messages
Every commit merged to main MUST follow Conventional Commits:
| Prefix | Effect |
|---|---|
fix: |
patch bump (x.y.Z) |
feat: |
minor bump (x.Y.0) |
feat!: or body with BREAKING CHANGE: |
major bump (X.0.0) |
chore: docs: style: refactor: perf: test: ci: build: |
no release |
Examples:
feat: add syntax highlighting option to code blocks
fix(code-highlight): honor alias spellings in languages whitelist
chore: bump dev dependencies
Workflow facts
release.ymlruns on Node 22 (semantic-release 25 requires Node ≥22.14).setup-nodeinrelease.ymlMUST NOT setregistry-url— semantic-release manages npm auth itself viaNPM_TOKEN. Settingregistry-urlcauses a 401 on whoami.ci.ymlruns the test matrix on Node 18 + 20 to match downstream users.- Commits authored by the release bot end with
[skip ci]and are filtered out by theif:guard inrelease.yml.
When the user asks to "cut a release" or "bump version"
Do NOT run npm version, edit package.json, or tag. Instead:
- Verify there are releasable commits since the last
v*tag (git log $(git describe --tags --abbrev=0)..HEAD --oneline). - If none, tell the user no
fix:/feat:commits exist yet and ask what change they want to ship. - If releasable commits already exist on
main, the release has either already happened or will on next push — no action needed.
See [RELEASING.md](../../RELEASING.md) for the full process and one-time repo setup.
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 · 52 lines · 12 tokens per session scan A 672ea389565b
releases is a cursor rule published in the GitHub repository MohtashamMurshid/md-to-docx (102 stars, last pushed yesterday), licensed MIT. It adds 12 tokens to every session and 565 once invoked, about $0.0001 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 cursor rules, from other repositories
monorepo-versioning
Internal peerDependency ranges and Changesets conventions for the SDK monorepo — avoid major-version cascades.
release-notes
Generate changelog entries and GitHub releases from git history. Categorizes commits into features, fixes, breaking changes, and docs. Supports conventional commits, PR-based grouping, and semantic versioning. Creates formatted CHANGELOG.md entries and GitHub releases.
iris
GitHub operations specialist — branches, pull requests, issues, releases, tags. Called by zeus after review. Never pushes or merges without explicit human approval. Integrates with VS Code GitHub Pull Requests extension.
release-checklist
What to update with each code change or version release.
release-policy
Release, versioning, and signing policy for setmac.
bump-project-version
The user can provide version in one of three ways.