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 glifxyz/glif-mcp-server --skill continue-projectgit clone --depth 1 https://github.com/glifxyz/glif-mcp-serverWrote 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/glifxyz/glif-mcp-server/continue-project)<a href="https://agentmods.dev/skills/glifxyz/glif-mcp-server/continue-project"><img src="https://agentmods.dev/badge/skills/glifxyz/glif-mcp-server/continue-project/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/glifxyz/glif-mcp-server/continue-project"><img src="https://agentmods.dev/badge/skills/glifxyz/glif-mcp-server/continue-project.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 | $0.00113 | $0.00686 |
| Opus 5.5 | $0.00045 | $0.00274 |
| Sonnet 5.5 | $0.00023 | $0.00137 |
| Haiku 4.5 | $0.00011 | $0.00069 |
Grade A, and why
continue-project 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.
What it actually says
Use this when the user wants to revisit or build on saved Glif work. The user's explicit instructions come first, within host safety rules.
- Find the project:
- From a link or ID the user gives you.
- Or with
list_projects, paging withcursoronly as far as needed. Read it withget_project. Setinclude_messagesonly when you need the history to understand the request. If several projects match, ask. If a project is missing or inaccessible, say so; do not guess other IDs or storage URLs.
- For a browse-only request, show the media links from
get_projectand stop. If the host renders Glif's viewer,view_mediawith theproject_id(and optionalasset_ids) reopens it there. Browsing never starts generation. - If
get_projectshows an active job, the project is already working. Do not start another. Follow it withget_job_statusonly if this conversation started that job; otherwise share the project link. - Work out what stays the same and what changes. Name the chosen media in the brief and keep the project's
project_id. Do not re-upload existing media just to copy it. Common follow-ups, each phrased as one clear change:- Variations: "Make 4 variations of image 2 that change only the background." Keep the count small unless the user asks for more.
- New format: "Same video, recomposed for 9:16 without cropping the subject."
- Targeted fix: "Fix only the headline text to read '...'. Keep everything else identical."
- Continuity: "Same character and style, new scene: ..." or "Next episode, same format and voice."
- If the user only asked to prepare a continuation, show the draft prompt and wait. Choosing media is not approval to spend.
- For a clear request to generate, note that it uses the account's Glif credits. Call
compose_projectwith theproject_idand the brief. Keep related outputs in one call. Leaveintelligenceunset so the project keeps its tier, unless the user asks to change it. - Share the
projectUrl. Callget_job_statuswith thejobIdasjob_iduntil the job finishes, and show new media as it arrives without repeats. Report the result or the failure. Never retry paid work on your own.
New work is added to the project. Originals stay untouched. Do not change account settings, buy credits or set up automatic generation while continuing a project.
What ships with it
1 file 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 · 26 lines · 113 tokens per session scan A 4ee92cf08d67
continue-project is a skill published in the GitHub repository glifxyz/glif-mcp-server (215 stars, last pushed 7d ago), licensed MIT. It adds 113 tokens to every session and 686 once invoked, about $0.0005 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 2026-10-08.
Other skills, from other repositories
beads
Use when working in a repository that uses bd or Beads for durable project task tracking, issue dependencies, blocker management, multi-session handoff, or shared work memory. Trigger when the user asks to find ready work, claim or close tasks, create follow-up work, inspect blockers, recover project context, or…
n8n-agents
Design n8n AI agents the right way. Use when building or editing any @n8n/n8n-nodes-langchain. AI node — an AI Agent, LLM chain, Text Classifier, or Information Extractor — and whenever the user mentions AI agents, LLM with tools, tool calling, $fromAI, system prompts, agent memory, sessionId, structured/JSON output…
n8n-subworkflows
Build reusable, composable n8n sub-workflows. Use when extracting shared logic, building anything multi-step or reused across workflows, or any workflow over 10 nodes — and whenever the user mentions sub-workflows, Execute Workflow, reuse, shared/common logic, modular workflows, "Define Below" inputs…
n8n-validation-expert
Interpret validation errors and guide fixing them. Use when encountering validation errors, validation warnings, false positives, operator structure issues, or need help understanding validation results. Also use when asking about validation profiles, error types, the validation loop process, or auto-fix capabilities.…
n8n-binary-and-data
Handle files and binary data in n8n correctly. Use when working with files, images, PDFs, attachments, uploads or downloads, base64, vision/multimodal input, or when an AI agent needs a file as tool input or output — and whenever the user mentions $binary, binaryPropertyName, "read the PDF", "attach the file", "send…
n8n-code-tool
Write JavaScript or Python for the n8n Custom Code Tool (@n8n/n8n-nodes-langchain.toolCode) — the AI-agent-callable tool, NOT the workflow Code node. Use when building a Code Tool attached to an AI Agent, writing code that an LLM will invoke, parsing the query input, returning a string result, defining an input schema…