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 ai-creed/ai-shakespii --skill using-shakespiigit clone --depth 1 https://github.com/ai-creed/ai-shakespiiWrote 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/ai-creed/ai-shakespii/using-shakespii)<a href="https://agentmods.dev/skills/ai-creed/ai-shakespii/using-shakespii"><img src="https://agentmods.dev/badge/skills/ai-creed/ai-shakespii/using-shakespii/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/ai-creed/ai-shakespii/using-shakespii"><img src="https://agentmods.dev/badge/skills/ai-creed/ai-shakespii/using-shakespii.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 | $0.00078 | $0.02759 |
| Opus 5.5 | $0.00031 | $0.01104 |
| Sonnet 5.5 | $0.00016 | $0.00552 |
| Haiku 4.5 | $0.00008 | $0.00276 |
Grade A, and why
using-shakespii 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 2mo 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 — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
using-shakespii
Intent
Teach an agent to drive the shakespii CLI — the deterministic lint and scaffold substrate for Agent Skills — so skills get created and repaired against the anatomy contract instead of by taste. The CLI decides; this skill teaches the loop around it.
Inputs
- Audit: the path to an existing skill directory (one containing
SKILL.md), or a corpus root — a directory of skill directories — audited in one run with--corpus. - Authoring: the new skill's kebab-case name, its purpose, and the situations that should trigger it — all three confirmed with the human before scaffolding.
- Optional: a specific finding or rule ID the human wants addressed first.
Preconditions
- Bun is installed and on PATH (
bun --versionsucceeds). - The shakespii CLI resolves: either installed globally (
bun add -g shakespii; the binary lands in~/.bun/bin), or the repo cloned and linked (bun install && bun linkinside it);shakespii --versionthen succeeds. - Audit: the target skill directory is readable.
- Authoring: the parent directory for the new skill is writable.
Procedure
Shared core, both branches:
- Run
shakespii lint <dir> --jsonand parse stdout (schemaversion: 1). Each finding carriesruleId,severity,file,line,message. - Exit codes:
0means no errors — proceed.1means errors — enter the fix loop.2means lint itself could not run — report the stderr message verbatim and stop; never guess around a broken run. - For each finding, look up its
ruleIdin references/rule-remediations.md and apply the minimal fix. A finding whose rule has no entry there is fixed from its ownmessage— messages are written to be actionable. - Re-lint. Loop until exit 0, then handle warnings: fix each one, or surface it to the human explicitly with a reason. Never silently ignore a warning.
Audit branch — fix an existing skill:
- Lint the directory the human named and work the fix loop above. For a corpus
root, run
shakespii lint <root> --corpus --json: work each skill's findings with the same loop, and treatcorpusFindings(XS rules, whosesitesname every involved skill) as refactor suggestions spanning skills. - Preserve the skill's voice and intent: reword a description to lead with its trigger; do not rewrite what the skill is for.
- Report before/after finding counts, what changed per rule, and any warnings left standing with reasons.
What ships with it
8 files 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.
- 2mo ago First seen · 224 lines · 78 tokens per session scan A d7c3ba8b8711
using-shakespii is a skill published in the GitHub repository ai-creed/ai-shakespii (2 stars, last pushed 3mo ago), licensed MIT. It adds 78 tokens to every session and 2,759 once invoked, about $0.0003 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
llm-as-judge-evaluation
Evaluate LLM outputs using frontier models as judges. Use for pairwise model comparison, quality scoring with custom rubrics, and automated evaluation pipelines. Covers position bias mitigation, statistical significance, and generating preference data for DPO/RLHF.
reproduce
Reproduces a paper's result, a claim, an artifact or a previous run with the target and success criterion frozen first, the canonical code path run before any substitute, exact inputs, environment, seeds and commands captured, and a verdict from a fixed set, reproduced, reproduced within tolerance, partially…
acceptance-checks
Turns the acceptance criteria a task states into executable checks and runs them against the finished outputs before delivering, rather than trusting that a correct-looking analysis satisfies them; rehearses the hidden condition when the grader scores unseen instances from a described family; treats a stated formula…
submitted-code
Writes code that survives being re-executed by someone else on inputs you never saw, targeting the grader's or collaborator's runtime rather than your own, with one self-contained entry point using only the libraries the specification names, no reliance on packages you installed or files you cached during development…
safe-extraction
Apply when extracting code from a large monolith file into submodules. Covers barrel re-exports, internals DI seam proxy patterns, CI invariant allowlist updates, and cross-file test verification. Prevents CI failures, broken imports, and test regressions from code extraction.
safe-rename
Workflow for safely renaming symbols (functions, types, classes, interfaces, constants, variables) across a codebase. Uses repomap, batchsymbols, and buildcheck to ensure every consumer is updated and nothing breaks.