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 agentmods add skills/ozmasterai/torus-framework/chainnpx skills add OZmasterAI/Torus-Framework --skill chaingit clone --depth 1 https://github.com/OZmasterAI/Torus-FrameworkWhat 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 | $0.00000 | $0.00879 |
| Opus 5 | $0.00000 | $0.00439 |
| Sonnet 5 | $0.00000 | $0.00176 |
| Haiku 4.5 | $0.00000 | $0.00088 |
Grade A, and why
chain 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/chain — Skill Composition Pipeline
When to use
When the user says "chain", "pipeline", "then", "sequence", "workflow", "run all", or wants to compose multiple skills into a sequential execution pipeline.
Examples:
/chain explore -> refactor -> test -> commit/chain review -> fix -> test/chain research -> build -> test -> deploy
Steps
1. PARSE CHAIN
- Parse skill names from the chain string by splitting on
->or→ - Trim whitespace from each skill name, strip any leading
/prefix - Validate each skill exists in
~/.claude/skill-library/(check forSKILL.md) - If any skill is missing, report which ones and abort
- Maximum chain length: 6 skills (reject longer chains with explanation)
- Show execution plan to user:
Chain: /skill_1 → /skill_2 → /skill_3 Steps: 3 | Mode: stop-on-failure - Wait for user confirmation before starting
2. MEMORY CHECK
search_knowledge("chain execution")— find prior chain runs and lessons learnedsearch_knowledge("[first skill in chain]")— check for known issues with lead skill- Note any past chain failures or gotchas to watch for during execution
3. EXECUTE SEQUENTIALLY
For each skill in the chain (N = current, M = total):
Announce:
━━━ Step N/M: Running /skill_name ━━━
Execute:
- Follow that skill's SKILL.md steps faithfully
- Memory context flows naturally — each skill's
remember_thiscalls are visible to subsequent skills viasearch_knowledge - SDK wrapping: Before each skill step, note the current
tool_call_countand time. After each step completes, compute elapsed time and tool calls used for that step. (Seehooks/shared/chain_sdk.py:ChainStepWrapperfor the utility class.)
On failure (tests fail, errors, tool failures):
- STOP the chain immediately
- Show what failed and why
- Ask the user:
- Continue — skip this skill, proceed to the next one
- Retry — re-run the current skill
- Abort — stop the chain entirely
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 First seen · 80 lines · 0 tokens per session scan A 43c698d90a3b
chain is a skill published in the GitHub repository OZmasterAI/Torus-Framework (5 stars, last pushed 3mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 879 tokens. 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…