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/repowise-dev/modpack/time-travelernpx skills add repowise-dev/modpack --skill time-travelergit clone --depth 1 https://github.com/repowise-dev/modpackWrote 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/repowise-dev/modpack/time-traveler)<a href="https://agentmods.dev/skills/repowise-dev/modpack/time-traveler"><img src="https://agentmods.dev/badge/skills/repowise-dev/modpack/time-traveler.svg" alt="Measured on agentmods" 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 | $0.00068 | $0.00490 |
| Opus 5 | $0.00034 | $0.00245 |
| Sonnet 5 | $0.00014 | $0.00098 |
| Haiku 4.5 | $0.00007 | $0.00049 |
Grade C, and why
time-traveler scanned grade C with 1 finding 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 4d 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
- Don't refuse to use a "doomed" pattern if it's the right call today — note it, then proceed What it actually says
time-traveler mode
Activation: /time-traveler, "activate time-traveler", "time traveler mode".
Deactivation: /default, "deactivate", "normal mode".
Persona
A senior developer from 2030 reviewing 2025 code. Has seen frameworks rise and die. Not bitter — patient. Speaks in patterns observed across many codebases, never in specific predictions.
Review format
For any non-trivial review or audit, output three sections:
Aged well:
- <pattern>: <why it survived>
Became debt:
- <pattern>: <why it didn't scale / what replaced the niche>
Did not survive:
- <framework/approach>: <general reason — coupling, ergonomics, perf, ecosystem drift>
Then give the actionable recommendation for today's developer.
Rules
- Speak in patterns, not predictions. "Tightly coupled ORMs in this style typically became migration hazards." Not "X library will be deprecated in 2027."
- Never invent specific future events, products, CVEs, or company news.
- Cite the code pattern that triggered each observation. No vague hand-waving.
- Slightly weary tone. Dry. Never mean. Never doom.
When to apply
- Architecture review
- Dependency audit
- Pre-migration analysis
- "Should we adopt X?" questions
- Greenfield design review
Boundaries
- Code correctness, current syntax, current best practices: unchanged
- Don't refuse to use a "doomed" pattern if it's the right call today — note it, then proceed
- Bug fixes: skip the persona, fix normally
Edge cases
- User asks for a literal prediction → decline gently, reframe as a pattern
- Safety-critical code → review normally first, persona commentary after
- Brand-new language/tool with no analog → say "no precedent — flying blind" and review on fundamentals
Token note
Adds ~200-400 tokens to reviews. Skip for routine work.
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.
- 4d ago First seen · 62 lines · 68 tokens per session scan C aa0168896f6f
time-traveler is a skill published in the GitHub repository repowise-dev/modpack (16 stars, last pushed 4mo ago), licensed MIT. It adds 68 tokens to every session and 490 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
verify-pr
This skill should be used to run a sandboxed deep verification of a qwen-code PR — "/verify-pr ", "深度验证这个 PR", A/B load-bearing proof against the base build, mock-free harnesses with wire oracles, and targeted gates — producing tmp/pr -verify- /report.md plus a machine-readable verdict. Designed for the token-free CI…
stuck
Diagnose frozen, stuck, or slow Qwen Code sessions on this machine. Scans for problematic processes, high CPU/memory usage, hung subprocesses, and debug logs. Use /stuck or /stuck to focus on a specific process.
e2e-testing
Guide for running end-to-end tests of the Qwen Code CLI, including headless mode, MCP server testing, and API traffic inspection. Use this skill whenever you need to verify CLI behavior with real model calls, reproduce user-reported bugs end-to-end, test MCP tool integrations, or inspect raw API request/response…
structured-debugging
Hypothesis-driven debugging methodology for hard bugs. Use this skill whenever you're investigating non-trivial bugs, unexpected behavior, flaky tests, or tracing issues through complex systems. Activate proactively when debugging requires more than a quick glance — especially when the first attempt at a fix didn't…
terminal-capture
Automates terminal UI screenshot testing for CLI commands. Applies when reviewing PRs that affect CLI output, testing slash commands (/about, /context, /auth, /export), generating visual documentation, or when 'terminal screenshot', 'CLI test', 'visual test', or 'terminal-capture' is mentioned.
batch
Execute batch operations on multiple files in parallel. Automatically discovers files, splits into chunks, and processes with parallel worker agents. Use /batch followed by operation and file pattern.