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 technicalpickles/pickled-claude-plugins --skill hk-creating-checksgit clone --depth 1 https://github.com/technicalpickles/pickled-claude-pluginsWrote 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/technicalpickles/pickled-claude-plugins/hk-creating-checks)<a href="https://agentmods.dev/skills/technicalpickles/pickled-claude-plugins/hk-creating-checks"><img src="https://agentmods.dev/badge/skills/technicalpickles/pickled-claude-plugins/hk-creating-checks/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/technicalpickles/pickled-claude-plugins/hk-creating-checks"><img src="https://agentmods.dev/badge/skills/technicalpickles/pickled-claude-plugins/hk-creating-checks.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 | $0.00111 | $0.01184 |
| Opus 5.5 | $0.00044 | $0.00474 |
| Sonnet 5.5 | $0.00022 | $0.00237 |
| Haiku 4.5 | $0.00011 | $0.00118 |
Grade A, and why
hk-creating-checks 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 8d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creating hk checks
A check is an hk step: a name, the files it applies to, and check / fix commands, defined in hk.pkl (hk's config, written in the Pkl language). This skill is about writing one that works on the hk version the project actually runs.
First: which hk?
Syntax and agent-safety features changed a lot between 1.x and 2.x. Find out before writing anything:
hk --version # the runtime
grep -m1 'hk@' hk.pkl # the schema the config amends ([email protected])
grep -n 'hk' mise.toml .mise.toml 2>/dev/null # what the project pins
The amends URL decides what syntax is valid; the binary decides what runs. They can disagree. Check references/versions.md for what each version supports. The short version:
| hk | What you can use |
|---|---|
| before 1.55 | String commands only. No effect, no --safe, no hk agent. |
| 1.55 and later | CommandSpec with effect, --safe, hk agent, hk mcp. |
| 2.0 and later | Top-level steps (implicit check, fix, pre-commit hooks), flat builtins with options, Pkl-only config. |
Workflow
- Look for a builtin first.
hk builtins | grep -i <tool>. UseBuiltins.<name>and override only what differs:(Builtins.ruff) { glob = List("src/**/*.py") }. Builtins already declare effects (1.55 and later). - Otherwise write a step. See references/step-anatomy.md for fields, command forms (shell string vs
argv), templates like{{files}}, andcheckvsfixvscheck_diff. - Declare the effect (1.55 and later), using
CommandSpec, hk's wrapper that lets a command carry aneffect.--saferefuses a step whose effect is unknown, and coding-agent hooks run--safe. See references/effects.md for how to chooseread,write, ordestructive. - Wire it into hooks. On 2.x, put it under top-level
stepsand it appears incheck,fix, andpre-commit. On 1.x, add it to eachhooks { ... steps { } }block. - Verify (below).
What ships with it
3 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.
- 8d ago First seen · 62 lines · 111 tokens per session scan A 814270f263a7
hk-creating-checks is a skill published in the GitHub repository technicalpickles/pickled-claude-plugins (12 stars, last pushed today), licensed MIT. It adds 111 tokens to every session and 1,184 once invoked, about $0.0004 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 2026-10-20.
Other skills, from other repositories
absolute-work
End-to-end, phase-gated SDLC for AI coding agents: relentless design interview → reviewed spec → dependency-graphed task board → safe-wave TDD execution → verification → converge. Handles features, bugs, refactors, greenfield projects, planning breakdowns, and migrations. Triggers on "absolute work", "build this…
absolute-deflake
Flaky test fixes: detect nondeterministic tests empirically (repeat/shuffle/parallel runs), diagnose the root cause, fix it — never retry/skip/sleep — and verify across many randomized runs. Triggers on "absolute deflake", "fix flaky tests", "CI is flaky", "this test fails randomly/intermittently".
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
testing
A guide for writing tests that check observable behaviour rather than the code's internal structure. Tests are repeatable checks that confirm software still gives the expected result after changes.
verify-and-fix
A development practice for checking that code really works before calling it finished. It uses tests, type checks, and real runs of the target scenario where available.
playwright-cli
A command-line tool for controlling Chromium, Firefox, and WebKit browsers, including navigation, page interaction, screenshots, PDFs, and recorded actions.