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 Alexander-Tyagunov/magician --skill portalgit clone --depth 1 https://github.com/Alexander-Tyagunov/magicianWrote 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/alexander-tyagunov/magician/portal)<a href="https://agentmods.dev/skills/alexander-tyagunov/magician/portal"><img src="https://agentmods.dev/badge/skills/alexander-tyagunov/magician/portal/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/alexander-tyagunov/magician/portal"><img src="https://agentmods.dev/badge/skills/alexander-tyagunov/magician/portal.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 | $0.00037 | $0.00207 |
| Opus 5 | $0.00018 | $0.00103 |
| Sonnet 5 | $0.00007 | $0.00041 |
| Haiku 4.5 | $0.00004 | $0.00021 |
Grade A, and why
portal 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 12d 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
$portal — Codex Adapter
Read ../../references/codex-adapter.md, then read ../../../skills/portal/SKILL.md and follow the source skill through that Codex adapter. Keep the source skill's gates, safety checks, and completion criteria.
Codex has no Magician WorktreeCreate hook in the shipped hook manifest. After creating a worktree, explicitly copy or summarize only the required task context into the dispatch prompt (Goal, Scope, approved plan/spec paths, constraints, verification, Return format), and point agents at repository AGENTS.md files. Do not copy Claude session state or claim automatic context propagation. Use a codex/ branch prefix unless the user requests another name, and report the absolute worktree path and cleanup command without running cleanup.
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.
- 12d ago First seen · 11 lines · 37 tokens per session scan A ed0f1eff66f2
portal is a skill published in the GitHub repository Alexander-Tyagunov/magician (14 stars, last pushed 11d ago), licensed MIT. It adds 37 tokens to every session and 207 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
g-doc-review
Documentation review gate. Dispatches the doc-reviewer agent on the changed file set to check documentation currency against the code it describes, then issues a standalone DOCS READY or DOCS HOLD verdict. On DOCS READY it writes the doc-approval sentinel that the commit gate checks for doc/mixed commits. Read-only on…
g-retro
Synthesize a session retrospective from the silent-observer journal — no interview. Reads the passive activity log (.claude/journal/), git history, and g-docs/todo.md, and writes g-docs/retros/YYYY-MM-DD-topic.md with what happened, decisions inferred, patterns, and cold-start context.
g-update
Fix G-Forge-managed files via Step 0 staleness preflight (stops with zero writes if cache lags GitHub, directs to /plugins first), then realigns CLAUDE.md Rules, agents, architecture rules, hooks, and native pre-commit gate. Safe — G-Forge markers only.
git-advanced-workflows
Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
no-mistakes
Validate committed feature-branch changes through the no-mistakes pipeline: intent, rebase, review, test, docs, lint, push, PR, and CI. Use when the user asks to run no-mistakes, ship safely, validate before pushing, or gate a change before it reaches upstream.