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 thierryc/Glyphs-mcp --skill glyphs-mcp-releasegit clone --depth 1 https://github.com/thierryc/Glyphs-mcpWrote 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/thierryc/glyphs-mcp/glyphs-mcp-release)<a href="https://agentmods.dev/skills/thierryc/glyphs-mcp/glyphs-mcp-release"><img src="https://agentmods.dev/badge/skills/thierryc/glyphs-mcp/glyphs-mcp-release/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/thierryc/glyphs-mcp/glyphs-mcp-release"><img src="https://agentmods.dev/badge/skills/thierryc/glyphs-mcp/glyphs-mcp-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 19 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00079 | $0.00952 |
| Opus 5 | $0.00039 | $0.00476 |
| Sonnet 5 | $0.00016 | $0.00190 |
| Haiku 4.5 | $0.00008 | $0.00095 |
Grade A, and why
glyphs-mcp-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 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.
Glyphs MCP Release
Treat preparation, signed artifact production, asset upload, and public release as separate authorization boundaries.
Establish the release state
- Work from the Glyphs MCP repository root. Read
CODEX.md, the current changelog, and the canonical release documentation before changing anything. - Inspect the branch, worktree, index, remotes, latest release tag, and divergence from
main. Preserve unrelated or uncommitted work; never discard it to make a release gate pass. - Identify the exact semantic version, installer build number, release base commit, intended branch, and requested phase. Default to local release-candidate preparation when the user has not authorized an external action.
- Record any safety stash or backup created during integration. Do not drop it until the restored tree and release candidate are verified.
Prepare the candidate
- Run
scripts/bump_version.py X.Y.Z, increment the integer installer build, and verify both plug-in plists, Xcode marketing/build versions, download links, and command-set version text. - Synchronize source and Plugin Manager runtime files using the repository packaging path appropriate to the change. Inspect the resulting diff; do not overwrite unrelated bundle work.
- Add every canonical skill to
scripts/sync_codex_plugin_skills.shandMANAGED_SKILL_NAMES, then run the synchronization script. Treatskills/as canonical andplugins/glyphs-mcp/skills/as generated. - Update
CHANGELOG.md, public setup/skill documentation, command/reference pages, andcontent/contributor/release-build-notes.mdx. Keep claims tied to tests actually run. - Update the production tool catalog, schemas, prompts, routing fixtures, and release-surface tests whenever a public tool or result contract changed.
Validate locally
- Run focused tests while iterating, then the complete local release gate with an accepted Python interpreter.
- Build the documentation website and validate every canonical and packaged skill with
quick_validate.py. - Run release metadata, catalog/documentation, installer, plug-in mirror, and packaged-skill synchronization checks. Run
git diff --checklast. - Perform the applicable manual matrix from the release QA protocol on disposable copies. Use Glyphs 3.5 and Glyphs 4 when compatibility is in scope.
- Never save an open font automatically. Snapshot document/file state for live read-only checks and report whether it remained unchanged.
- For staging-only updater releases, require Prepare Update wording, an explicit not-installed state, a trusted release link, and proof that the installed plug-in remains unchanged.
What ships with it
2 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.
- 12d ago First seen · 52 lines · 79 tokens per session scan A da4999257b9e
glyphs-mcp-release is a skill published in the GitHub repository thierryc/Glyphs-mcp (44 stars, last pushed 2d ago), licensed Apache-2.0. It adds 79 tokens to every session and 952 once invoked, about $0.0004 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
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
updater_guide
Guidance for checking for and installing Row-Bot updates.