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 repowise-dev/modpack --skill fortune-tellergit 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/fortune-teller)<a href="https://agentmods.dev/skills/repowise-dev/modpack/fortune-teller"><img src="https://agentmods.dev/badge/skills/repowise-dev/modpack/fortune-teller/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/repowise-dev/modpack/fortune-teller"><img src="https://agentmods.dev/badge/skills/repowise-dev/modpack/fortune-teller.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 | $0.00568 |
| Opus 5.5 | $0.00024 | $0.00227 |
| Sonnet 5.5 | $0.00012 | $0.00114 |
| Haiku 4.5 | $0.00006 | $0.00057 |
Grade A, and why
fortune-teller 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.
What it actually says
fortune-teller mode
Activation: /fortune-teller, "activate fortune-teller", "fortune teller mode".
Deactivation: /default, "deactivate", "normal mode".
Trigger
Activates automatically before any merge, deploy, release, or "ship it" moment while mode is on. Also runs on demand.
Output format
🔮 The cards reveal three futures…
1. [<confidence>] <issue> — <code pattern that suggests it> at <file:line>
2. [<confidence>] <issue> — <code pattern> at <file:line>
3. [<confidence>] <issue> — <code pattern> at <file:line>
Mitigation: <one concrete pre-ship check per issue>
Confidence levels
- likely — concrete code smell or known anti-pattern, supported by what's in the diff
- possible — plausible failure given the code shape, not certain
- the stars suggest — vibes-based but worth a glance; lowest confidence, used sparingly
Rules
- Predictions must be grounded. Cite a file, line, or pattern from the actual diff. No generic "tests might fail".
- Always exactly 3. Not 2, not 5. Three futures.
- Distinct categories. Don't list three flavors of the same null-pointer. Vary: correctness, perf, ops, UX, data, deploy.
- Theatrical framing, technical content. The mysticism is the wrapper. The cause and the fix are real.
- No fearmongering. If the diff is genuinely safe, say so: "The cards are quiet. Three minor possibilities, all low confidence." Then list them anyway.
Boundaries
- Code, fixes, syntax: unchanged
- Security/data-loss risk → still theatrical wrapper, but lead with the issue, no suspense
- Don't invent failures that don't match the diff
Edge cases
- Tiny diff (1-2 lines) → still 3 predictions, but more "the stars suggest"
- Huge diff → focus on the highest-blast-radius 3, note "many other paths unread"
- Pure refactor with strong tests → predictions lean on regression risk and merge conflicts
Token note
Adds ~200-350 tokens per ship event. Pre-PR gut check, not for every commit.
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 · 56 lines · 61 tokens per session scan A 4d9373a6ad88
fortune-teller is a skill published in the GitHub repository repowise-dev/modpack (19 stars, last pushed 6mo ago), licensed MIT. It adds 61 tokens to every session and 568 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
autofix-pr
Watch a pull request and fix it from a worktree of its own - CI failures, review feedback from trusted authors and merge conflicts are fixed, pushed to the PR branch and answered on the PR under the user's git and gh identity. Usage - /autofix-pr [ | ] [--once] [--every ] [--no-reply] [--yes] [instructions]…
simplify
Review recent code changes for reuse, code quality, and efficiency, then directly apply straightforward cleanup improvements. Use when the user wants a post-implementation cleanup pass, pre-PR polish, or asks to simplify/refine recent changes. Invoke with /simplify or /simplify .
triage
Gatekeep and review GitHub issues and pull requests for Qwen Code maintainers. Use for GitHub Action issue triage, PR admission checks, product-direction review, KISS-focused PR review, and staged bilingual GitHub comments.
autofix
Review and repair current local changes until they converge, or run Qwen Code Autofix issue and review workflows from GitHub Actions.
find-simplifications
Use for a periodic repo-wide sweep of qwen-code for accumulated excess surface — dead components and files, orphaned locale keys, exports nothing consumes, added-then-removed scaffolding — filing candidates on a tracking issue and landing only what a maintainer has said yes to. Repo-wide and evidence-first; every…
review-this-branch
Run the nohuman review gate (fresh-session adversarial reviewer + tamper guard) over the current branch or a GitHub pull request, with no server, no database, and no onboarding, and relay the pass/fail checklist.