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-macro-iterationgit 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-macro-iteration)<a href="https://agentmods.dev/skills/thierryc/glyphs-mcp/glyphs-macro-iteration"><img src="https://agentmods.dev/badge/skills/thierryc/glyphs-mcp/glyphs-macro-iteration/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-macro-iteration"><img src="https://agentmods.dev/badge/skills/thierryc/glyphs-mcp/glyphs-macro-iteration.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 | $0.00049 | $0.01284 |
| Opus 5.5 | $0.00020 | $0.00514 |
| Sonnet 5.5 | $0.00010 | $0.00257 |
| Haiku 4.5 | $0.00005 | $0.00128 |
Grade A, and why
glyphs-macro-iteration 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 8d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visible macro iteration
Use this optional companion when the user wants to see and iterate on script code inside Glyphs. Ordinary one-off font operations remain with $glyphs-mcp-scripting; ongoing script or plugin development uses $glyphs-mcp-development. Reuse guidance already loaded. This skill adds no MCP tools and requires a local Glyphs 4 UI automation surface for agent-driven interaction. Without that surface, prepare the workspace revision and explain the manual steps; do not claim native execution or console capture. Resolve the required scripting guidance from its installed location if sibling links are unavailable.
The workspace file is authoritative. The goal is to make the intended revision visible, run it under existing task authorization, capture attributable output, and verify behavior before revising again. See qualified behavior and limits when choosing the loading/capture route or reporting host support.
Prepare the intended revision
Follow the scripting skill for API documentation, static validation, pure logic, precision, task scope and result checks. Writing or reviewing alone does not authorize execution. Do not turn a coding session into an MCP server change.
Distinguish execution contexts before loading code. An MCP run(layer, params, context) callback or font-level entrypoint is not automatically invoked by the
Scripting Window, and its injected arguments are not supplied there. For a
requested standalone macro, provide an explicit native entrypoint with exact
target checks. Do not silently convert an MCP job to manual execution or imply
that opening its source reproduces its execution environment.
Use tests proportional to the script: expected behavior and preservation checks for meaningful transformations, pure tests for calculations, and read-only preflight checks before native writes. Preflight validates prerequisites; it is not evidence of test-driven development or successful execution. Experiments that mutate fonts use disposable fixtures under the existing development guidance. Repeated execution must start from a known state or deliberately test repeat-run behavior.
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.
- 8d ago First seen · 107 lines · 49 tokens per session scan A cb1c30fb65d3
glyphs-macro-iteration is a skill published in the GitHub repository thierryc/Glyphs-mcp (54 stars, last pushed today), licensed Apache-2.0. It adds 49 tokens to every session and 1,284 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-13.
Other skills, from other repositories
html-ppt-zhangzara-block-frame
Rescuing a messy startup deck into a board-grade system — the diagnosis, the page grammar, and the rebuilt proof pages. Built as a decision-grade design craft deck for founders, exec presenter.
accesslint-scan
Audit a live page for accessibility issues, locate each WCAG violation precisely, and return a selector-grounded fix worklist without editing.
check
Reviews diffs, PRs, release readiness, and publishing follow-through. Use when asked to review, triage issues or PRs, or ship. Not for debugging root causes or prose.
health
Audits agent config, instruction drift, hooks or MCP, and AI maintainability. Use when Claude, Codex, or Pi setup looks wrong. Not for application bugs or PR review.
hunt
Finds root cause before any fix. Use when something errors, crashes, regresses, or used to work. Not for code review or new features.
think
Turns rough ideas into approved, decision-complete plans before coding. Use when planning architecture, judging whether to build, or writing a handoff. Not for bug fixes or small edits.