Borrowing it
Nothing to install: this file belongs to Athroniaeth/piighost. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Athroniaeth/piighost/master/.claude/skills/piighost-code-style/SKILL.mdgit clone --depth 1 https://github.com/Athroniaeth/piighostWrote 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/athroniaeth/piighost/piighost-code-style)<a href="https://agentmods.dev/skills/athroniaeth/piighost/piighost-code-style"><img src="https://agentmods.dev/badge/skills/athroniaeth/piighost/piighost-code-style/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/athroniaeth/piighost/piighost-code-style"><img src="https://agentmods.dev/badge/skills/athroniaeth/piighost/piighost-code-style.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00000 | $0.06216 |
| Opus 5 | $0.00000 | $0.03108 |
| Sonnet 5 | $0.00000 | $0.01243 |
| Haiku 4.5 | $0.00000 | $0.00622 |
Grade A, and why
piighost-code-style 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 9d 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 — 739 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PIIGhost code style
Overview
PEP8 and ruff already enforce formatting (line length, import order, quotes, trailing commas). This skill captures the conventions that tooling does not enforce: how the maintainer prefers expressions, dispatch, and naming to be written. They are taste rules, gathered from review feedback.
Apply them whenever you write or refactor code. When a rule conflicts with an established local pattern, match the surrounding code and flag the tension rather than rewriting silently.
This skill grows. When the maintainer states a new preference during a
review, add it here as a new numbered rule with an Avoid -> Prefer pair and a
one-line why. Keep the existing entries; do not renumber on every edit.
Rules
1. Prefer a named local + or over a None-guard ternary
When falling back to a default and the falsy-but-not-None edge (e.g. the empty
string) is irrelevant, bind a named local with or instead of an inline
x if x is not None else y.
Avoid:
return {"text": redact_as if redact_as is not None else self.text, ...}
self.detections = detections if detections is not None else []
Prefer:
text = redact_as or self.text
return {"text": text, ...}
self.detections = detections or []
Why: the named local reads like a sentence and or is shorter. This holds for
a constructor defaulting an optional argument to an empty collection too:
self.x = arg or [], not the ternary. Only keep is not None when an
empty/zero value must be preserved distinctly from the default, and add a
comment saying so when you do.
2. Prefer a data-driven dict over an if/elif dispatch cascade
When selecting one of N things by a key, use a dict lookup, not a chain of
if key == ...: return .... A dict is O(1), auditable at a glance, and adding a
case is a single line.
Avoid:
def _resolve_lazy_detector(key):
if key == "lazy:gliner2":
from piighost.detector.gliner2 import Gliner2Detector
return Gliner2Detector
if key == "lazy:spacy":
from piighost.detector.spacy import SpacyDetector
return SpacyDetector
raise KeyError(key)
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.
- 9d ago First seen · 739 lines · 0 tokens per session scan A 2b30d288507b
piighost-code-style is a skill published in the GitHub repository Athroniaeth/piighost (13 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 6,216 tokens. 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
code-review
Perform a structured code review of changes, checking for correctness, style, tests, and potential issues.
cli-command
Design, implement, or review Composio CLI commands under ts/packages/cli using Effect, @effect/cli, services, output conventions, configuration and environment variables, and local vendor references. Use for CLI command UX, command wiring, service changes, or CLI source edits. Do not use for CLI E2E-only work; use…
review
Structured PR review for pygraphistry. Input: PR number/branch (default current branch PR). Output: findings and convergence artifacts under plans/ /. Method: multi-wave, evidence-first review across spec, correctness, tests, security, code quality, DRY, concurrency, performance, architecture, operability, and…
red-team-review
Unified adversarial review: v4.3 Strategic Matrix (MTA-004). 7-phase framework: Priors → Rubric → Adversarial Lenses → SWOT/TOWS → MCDA Decision Engine → Blind Spot/Kill Switch → Executive Summary. Absorbs: bias-detector.
code-review
Review diffs and change sets for bugs, regressions, risks, and missing tests.
check
Run the full local quality gate (prek hooks + tox test matrix) before committing or opening a pull request. Use when asked to "check", "lint", "run CI locally", or verify a change is ready.