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 dpc00/sublime-mcp --skill package-skill-generatorgit clone --depth 1 https://github.com/dpc00/sublime-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/dpc00/sublime-mcp/package-skill-generator)<a href="https://agentmods.dev/skills/dpc00/sublime-mcp/package-skill-generator"><img src="https://agentmods.dev/badge/skills/dpc00/sublime-mcp/package-skill-generator/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/dpc00/sublime-mcp/package-skill-generator"><img src="https://agentmods.dev/badge/skills/dpc00/sublime-mcp/package-skill-generator.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 | $0.00089 | $0.01539 |
| Opus 5.5 | $0.00036 | $0.00616 |
| Sonnet 5.5 | $0.00018 | $0.00308 |
| Haiku 4.5 | $0.00009 | $0.00154 |
Grade A, and why
package-skill-generator 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.
How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Package Skill Generator
Produces a skill file (SKILL.md, standard Agent Skills format --
folder + frontmatter, no code) documenting exactly how to control one
target Sublime package directly through sublime-mcp's own generic tools
(get_package_mcp_info, run_command, eval_python) -- not a standalone
MCP server.
Why a skill instead of a server, and when that's not the answer:
confirmed directly (2026-09-08, against three real, structurally different
packages -- Debugger, GotoRelated, OpenFileOverSSH) that the generic loop
(discover -> read the target's real source -> call it with run_command/
eval_python) is sufficient on its own for an agent that already has that
generic access. A dedicated MCP server was never actually required for
control in any of those three cases -- confirmed by directly reading even
debugger-mcp's own deepest handlers (e.g. mcp_debugger_get_variables),
which turned out to be a couple of lines wrapping core.run(...), not
bespoke logic that justified a ~2,000-line standalone package. A skill
captures the one genuinely valuable thing those bigger builds were for --
the investigation (the real dispatch table, the async-bridging trick,
the object graph) -- as cheap, editable text instead of a server.
A standalone server (see the older package-mcp-generator skill, kept for
this case) is still the right call in the narrow case a skill can't cover:
a client with no eval_python-equivalent of its own, or a capability
that must be reachable independent of any particular agent session. Ask
which situation this is before picking a path -- default to a skill.
Step 0 — check for an existing skill first
Look in the environment's own skills location (for Claude Code, in the
absence of other instruction, ~/.claude/skills/<name>/) for one already
covering this package. If one exists, read and update it rather than
generating a duplicate.
Step 1 — introspect, but do not stop there
Same investigative work as before, because it's the part that's actually valuable, independent of what the output format is:
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.
- 2d ago Changed b99c1ffe461a
- 1mo ago First seen · 124 lines · 89 tokens per session scan A 901784260319
package-skill-generator is a skill published in the GitHub repository dpc00/sublime-mcp (4 stars, last pushed today), licensed MIT. It adds 89 tokens to every session and 1,539 once invoked, about $0.0004 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 2026-09-09.
Other skills, from other repositories
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — Diagnostics issues first, then errors, failed tool calls, latency, regressions, and low online-eval scores. With the Opik MCP connected it lists the project's agentinsightsissue entities, offers to turn Diagnostics on when the project has it…
lsp-implement
Find all concrete implementations of an interface or abstract type. Use when you need to know what types satisfy an interface, or what subtypes exist before changing a base type.
quantum-grover
A Qiskit implementation of Grover's algorithm, a quantum search method that increases the chance of finding a marked item. It can explain the method, build an explicit quantum circuit, or run it with chosen inputs.
dcc-blender-assembly-pitfalls
Read this BEFORE writing any Blender geometry code through MCP, whenever you are about to (1) create or size mesh primitives - bpy.ops.mesh.primitivecubeadd, primitivecylinderadd, primitiveuvsphereadd, primitiveconeadd - or set scale / dimensions on a part; (2) orient a part with rotationeuler or rotationquaternion…
linkding
Manage bookmarks with Linkding. Use when the user asks to "save a bookmark", "add link", "search bookmarks", "list my bookmarks", "find saved links", "tag a bookmark", "archive bookmark", "check if URL is saved", "list tags", "create bundle", or mentions Linkding bookmark management.
quantum-algorithms
A routing workflow for choosing an open-source quantum-computing algorithm and loading the matching local workflow. Quantum computing uses circuits and quantum states to represent and process information.