Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add gustavo-meilus/superpipelines/plugin install superpipelinesWrote 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/gustavo-meilus/superpipelines/sk-platform-dispatch)<a href="https://agentmods.dev/skills/gustavo-meilus/superpipelines/sk-platform-dispatch"><img src="https://agentmods.dev/badge/skills/gustavo-meilus/superpipelines/sk-platform-dispatch/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/gustavo-meilus/superpipelines/sk-platform-dispatch"><img src="https://agentmods.dev/badge/skills/gustavo-meilus/superpipelines/sk-platform-dispatch.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 | $0.00061 | $0.08159 |
| Opus 5 | $0.00030 | $0.04079 |
| Sonnet 5 | $0.00012 | $0.01632 |
| Haiku 4.5 | $0.00006 | $0.00816 |
Grade A, and why
sk-platform-dispatch scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 485 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Platform Dispatch — Tier Detection & Tier 2 Inline Execution
Tier Detection Protocol
Detection heuristics run in order — first match wins. Override: SUPERPIPELINES_FORCE_TIER env var, when set to a known tier id (tier_1 | tier_1b | tier_1c | tier_1d | tier_2), bypasses all heuristics. Use when detection picks the wrong tier in a multi-platform workspace.
- Tier 1 (Claude Code):
Tasktool present ANDsubagent_typeparameter accepted. Secondary:CLAUDE_CODEenv var set OR.claude-plugin/plugin.jsonresolvable via${CLAUDE_PLUGIN_ROOT}. (Runtime capability is the primary signal; the secondary check is acceptable here because DETECT() runs in the live runtime where the Task primitive can be probed directly.) - Tier 1b (OpenCode):
$OPENCODE_CONFIG_DIRenv var set OR agent files usingmode: subagentfrontmatter present under the active scope root. - Tier 1c (Antigravity):
agybinary on PATH. - Tier 1d (Codex):
codexbinary on PATH OR.codex-plugin/plugin.jsonresolvable. - Tier 2 (fallback): None of the above. Safe default — sequential inline execution always works.
What ships with it
35 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.
- fixtures/cc-materialize/expected-cc/doc-reviewer.md 920 B
- fixtures/cc-materialize/expected-cc/doc-writer.md 932 B
- fixtures/cc-materialize/expected-cc/triage-probe.md 822 B
- fixtures/cc-materialize/input/doc-reviewer.cad.md 1.3 KB
- fixtures/cc-materialize/input/doc-writer.cad.md 1.2 KB
- fixtures/cc-materialize/input/resolved-models.json 633 B
- fixtures/cc-materialize/input/triage-probe.cad.md 1.1 KB
- fixtures/cc-materialize/README.md 3.5 KB
- fixtures/codex-materialize/expected-codex/doc-reviewer.toml 902 B
- fixtures/codex-materialize/expected-codex/doc-writer.toml 959 B
- fixtures/codex-materialize/expected-codex/triage-probe.toml 809 B
- fixtures/codex-materialize/input/doc-reviewer.cad.md 1.3 KB
- fixtures/codex-materialize/input/doc-writer.cad.md 1.2 KB
- fixtures/codex-materialize/input/resolved-models.json 651 B
- fixtures/codex-materialize/input/triage-probe.cad.md 1.1 KB
- fixtures/codex-materialize/README.md 3.6 KB
- fixtures/non-materializing-dispatch/input/doc-reviewer.cad.md 1.3 KB
- fixtures/non-materializing-dispatch/input/doc-writer.cad.md 1.2 KB
- fixtures/non-materializing-dispatch/README.md 2.8 KB
- fixtures/oc-materialize/expected-oc/doc-reviewer.md 958 B
- fixtures/oc-materialize/expected-oc/doc-writer.md 952 B
- fixtures/oc-materialize/input/doc-reviewer.cad.md 1.3 KB
- fixtures/oc-materialize/input/doc-writer.cad.md 1.2 KB
- fixtures/oc-materialize/input/resolved-models.json 467 B
- fixtures/oc-materialize/README.md 3.0 KB
- profiles/fixtures/invalid/missing-model-tier-deep.json 898 B
- profiles/fixtures/invalid/missing-required-field.json 929 B
- profiles/fixtures/invalid/stray-capability-field.json 1022 B
- profiles/fixtures/valid/tier1-minimal.json 1.1 KB
- profiles/profile.schema.json 3.9 KB
- profiles/tier_1.json 1.2 KB
- profiles/tier_1b.json 1.9 KB
- profiles/tier_1c.json 2.3 KB
- profiles/tier_1d.json 2.5 KB
- profiles/tier_2.json 2.2 KB
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.
- 5d ago First seen · 485 lines · 61 tokens per session scan A e6a3196abd1b
sk-platform-dispatch is a skill published in the GitHub repository gustavo-meilus/superpipelines (4 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 8,159 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
Email Composer
Draft professional emails for various contexts including business, technical, and customer communication. Use when the user needs help writing emails or composing professional messages.
Excel Analysis
Analyze Excel spreadsheets, create pivot tables, generate charts, and perform data analysis. Use when analyzing Excel files, spreadsheets, tabular data, or .xlsx files.
Git Commit Helper
Generate descriptive commit messages by analyzing git diffs. Use when the user asks for help writing commit messages or reviewing staged changes.
multi-agent-skill-sharing
Install a skill once and make it usable across multiple AI coding agents (Claude Code, Codex CLI, Cursor, Gemini CLI, Cline, etc.) that work on the same repository. Use this when the user wants a skill / ruleset / prompt to be shared and switchable across several AI products, asks "why can only one tool use this…
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
xlsx
Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify…