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 gustavo-meilus/superpipelines --skill change-modelsgit clone --depth 1 https://github.com/gustavo-meilus/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/change-models)<a href="https://agentmods.dev/skills/gustavo-meilus/superpipelines/change-models"><img src="https://agentmods.dev/badge/skills/gustavo-meilus/superpipelines/change-models/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/change-models"><img src="https://agentmods.dev/badge/skills/gustavo-meilus/superpipelines/change-models.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 | $0.00021 | $0.02175 |
| Opus 5.5 | $0.00008 | $0.00870 |
| Sonnet 5.5 | $0.00004 | $0.00435 |
| Haiku 4.5 | $0.00002 | $0.00217 |
Grade A, and why
change-models 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 1mo 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Change Models — Multi-Platform Model Preference Management
Workflow
PHASE 0 — Scope Detection
- Load
sk-platform-dispatch→DETECT()→platform_profile. - Enumerate scope roots that exist in the workspace:
<workspace>/.claude/,<workspace>/.opencode/,<workspace>/.agents/,<workspace>/.superpipelines/
- For each existing root, scan
<root>/superpipelines/registry.jsonfor pipelines. - If no pipelines anywhere AND no preference files: only Mode E (first-run wizard) is offered.
- Present platform context: "Active platform: <profile.name> (<profile.tier>). Pipelines found in: ."
PHASE 1 — Mode Selection
Present seven modes:
| Mode | Action |
|---|---|
| A — User-global prefs | Edit ~/.superpipelines/model-preferences.json; bump model_tiers_version_acked |
| B — Workspace prefs | Edit <workspace>/.superpipelines/model-preferences.json |
C — Per-agent model_tier: override |
Edit agent frontmatter |
D — Per-agent explicit model: (escape hatch, advanced) |
Edit agent frontmatter; surfaces SEV-3 audit warning |
| E — First-run wizard | Interactive 4-tier setup with subscription detection |
| F — Catalog refresh | Reconcile prefs with new profile model_tiers_version |
| G (Q6) — Orchestrator-tier override | Set the orchestrator-only model tier on platforms where per-step assignment is meaningless (dynamic_subagents: true or model_field_format: "omit"). Writes to user or workspace prefs at platforms[tier].orchestrator_tier. |
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.
- 1mo ago First seen · 167 lines · 21 tokens per session scan A 2a5cbf626de8
change-models is a skill published in the GitHub repository gustavo-meilus/superpipelines (4 stars, last pushed 3mo ago), licensed MIT. It adds 21 tokens to every session and 2,175 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
answer-audit
Adversarially audit a RAG answer against the corpus it claims to cite. Use when asked to review, critique, sanity-check, or "give skeptical feedback on" an answer produced by Canon (or any retrieval-grounded system) — especially when the answer looks good. Assumes the answer is wrong until each claim is proven…
compendium-lint
Use to gardening-check a Compendium-style controlled-vocabulary store before committing or publishing it — verifying pointer integrity, register discipline, and store health. Invoke after adding/editing entries, on a cadence, or before a release that touches the vocabulary store. Runs the deterministic lint.cjs if the…
x-bug2rag
A knowledge-capture tool that turns reusable bug explanations into a local RAG collection, meaning a searchable store of text that an agent can retrieve later. It records the trigger, incorrect implementation, correct implementation, and observable difference.
x-dev-rag-call
A local semantic search tool that finds relevant passages in specified Markdown or text files. It uses an embedding model, which represents meaning as numbers, to return the closest passages for a question or plan.
pocket-development
Execute Pocket implementation plans through bounded packets, delegated implementation, independent review, and phase handoff. Use when the user asks to execute a plan or dispatch its tasks.
pocket-pitching
Pre-grinding problem exploration. Use BEFORE pocket-grinding when the problem is unformed or needs exploration. Guides diverge→converge with structured brainstorming methods and independent advisor curation (advisor tool or advisor subagent fallback), then produces a pitch exploration doc. Trigger on…