A release procedure for Framelink MCP for Figma, the server that gives AI coding tools access to Figma design data. It checks the automated release pull request, summarizes its changes, and asks before merging it.

Use it to find a pending release, review the version and changelog, inspect the difference when needed, and merge the approved release using the project's required method.

It reduces the chance of publishing the wrong version or merging a release without reviewing its included changes.

release — Command by GLips

Install

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.

agentmods

npx agentmods add commands/glips/figma-context-mcp/release

Clone the repo

git clone --depth 1 https://github.com/GLips/Figma-Context-MCP

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 590 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00000	$0.00590
Opus 5	$0.00000	$0.00295
Sonnet 5	$0.00000	$0.00118
Haiku 4.5	$0.00000	$0.00059

Measured 2d ago against content hash 1357be5e3538, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

release 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 2d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

release — 100% identical, 0 lines differ

.claude/commands/release.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release

Review and publish a new release.

Steps

Check for a release-please PR: Run gh pr list --repo GLips/Figma-Context-MCP --label "autorelease: pending" --json number,title,url to find the open release PR.

If no release PR exists, inform the user: "No pending release PR. Release-please creates one automatically when conventional commits (fix:, feat:) land on main."
Show what's in the release: Run gh pr view <number> --json body to display the pending changelog and version bump. Summarize:
- New version number
- Number of features, fixes, and other changes
- List of included commits
Ask for confirmation: Use AskUserQuestion: "Merge this release PR to publish v to npm?"
- Merge and publish — Proceed with merge
- Review diff first — Show gh pr diff <number>
- Cancel — Stop without merging
Merge the release PR: Run gh pr merge <number> --rebase --repo GLips/Figma-Context-MCP (or merge via the GitHub UI).

Use rebase, not squash. Feature PRs are squash-merged (so each conventional-commit title, with its (#NNN), feeds the changelog), but the release PR is the single chore(main): release X.Y.Z commit release-please authored. Rebase replays it onto main verbatim — bot authorship, clean subject, no (#NNN). Squash would rewrite all three and diverge from every prior release (check git log for chore(main): release commits — they're all single-parent, bot-authored, no PR suffix). Merging through the UI does the same thing.
Verify: Run gh run list --repo GLips/Figma-Context-MCP --limit 1 to confirm the Release workflow triggered. Report the workflow run URL so the user can monitor npm publish.

The Release workflow also bumps server.json and publishes to npm (OIDC) and the MCP registry — all hands-off. No manual steps beyond merging the PR.
Write the curated release notes: Once the workflow has published the GitHub Release (the tag exists), run /release-notes to replace the mechanical, auto-generated Release body with brand-voice highlights. release-please only produces a terse commit-title list; /release-notes turns it into something worth reading. CHANGELOG.md is left as-is — release-please owns it.

Read the full file on GitHub · 48 lines

Changes

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.

2d ago First seen · 48 lines · 0 tokens per session scan A 1357be5e3538

Subscribe to this mod's changes

release is a command published in the GitHub repository GLips/Figma-Context-MCP (15,752 stars, last pushed 26d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 590 tokens. 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.

Code review Git and workflow Languages ai cursor figma mcp typescript

review-code

Read ALL memory bank code rules + best practices, check the files that changed, and APPLY fixes so they adhere. The active counterpart to /scan (which is read-only). Use after an AI session, before commit, to make changed files compliant.

chohra-med/expo_boilerplate · 50 tokens

rules

Command "rules" from chohra-med/expo_boilerplate, covering invocation, what a "rules-boundary" directory is, the five sections (one owner agent each), generate (the "create them if they don't exist" path) and resolve (what each agent reads).

chohra-med/expo_boilerplate · 0 tokens

init

Command "init" from chohra-med/expo_boilerplate, covering command: init — spec-driven bootstrap, invocation, step 1 — capture intent (the interview, one message), step 2 — scaffold (copy from templates/, fill the {{...}}) and step 4 — write the first spec from the goal.