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 Firstp1ck/pi-coding-agent-forge --skill code-qualitygit clone --depth 1 https://github.com/Firstp1ck/pi-coding-agent-forgeWrote 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/firstp1ck/pi-coding-agent-forge/code-quality)<a href="https://agentmods.dev/skills/firstp1ck/pi-coding-agent-forge/code-quality"><img src="https://agentmods.dev/badge/skills/firstp1ck/pi-coding-agent-forge/code-quality/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/firstp1ck/pi-coding-agent-forge/code-quality"><img src="https://agentmods.dev/badge/skills/firstp1ck/pi-coding-agent-forge/code-quality.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 | $0.00082 | $0.01783 |
| Opus 5.5 | $0.00033 | $0.00713 |
| Sonnet 5.5 | $0.00016 | $0.00357 |
| Haiku 4.5 | $0.00008 | $0.00178 |
Grade A, and why
code-quality 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.
This is a copy
89% identical to code-quality — 252 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Quality
Write code that is correct, clear, and easy to change. Improve it as you write it, rather than leaving avoidable problems for a later review.
Always apply to permanent code
Load this skill before creating or editing code that will remain in a file. Apply it throughout the task and to every subsequent code write. A one-line fix is not exempt. You do not need to reload unchanged instructions before each write.
Permanent means intended to survive the task, whether tracked by Git or not. This includes application and library source, scripts, tests and fixtures, saved examples, migrations, notebook code cells, configuration-as-code, and code embedded in retained HTML, templates or documentation. Apply it when promoting a temporary prototype into a permanent file, too.
The writing method does not matter: direct writes, edits, patches, generated code and delegated implementation all follow the same standard. Give delegated writers this requirement within their assigned scope. For generated or vendored output, respect repository policy and improve the authorized source or generator instead of hand-editing protected artifacts.
Prose-only changes, explanations or code snippets shown only in chat, and disposable scratch experiments with no retained code do not require this skill. Explicit code-quality reviews still use its inspection criteria.
This is an always-apply instruction for the agent, not a filesystem hook. The skill does not intercept writes or guarantee that a model invokes it. It does not require a scanner run, extra edits or a formal report for every save.
Work inside the requested task
A request to write or change code authorizes applying these quality practices to that code. Make justified local improvements directly; do not ask for a separate cleanup approval merely to write the requested code well.
An explicit review-only or do not edit request stays read-only. Inspect and explain findings without applying them. Loading the skill never grants permission to write code when the user only asked a question or requested a review.
What ships with it
14 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.
- references/language-checks.md 4.8 KB
- references/measurement-guide.md 2.6 KB
- rules/ast-grep/javascript/no-console-log.yml 137 B
- rules/ast-grep/python/inspect-print.yml 119 B
- rules/ast-grep/typescript/no-console-log.yml 140 B
- scripts/adapters/ast-grep.mjs 8.9 KB runs code
- scripts/adapters/jscpd.mjs 9.7 KB runs code
- scripts/lib/capture.mjs 46 KB runs code
- scripts/lib/classification.mjs 7.8 KB runs code
- scripts/lib/git.mjs 26 KB runs code
- scripts/lib/metrics.mjs 12 KB runs code
- scripts/lib/report.mjs 33 KB runs code
- scripts/lib/runner.mjs 14 KB runs code
- scripts/scan.mjs 19 KB runs code
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 Changed · -145 lines · +33 tokens per session e4aa9929e9af
- 1mo ago First seen · 245 lines · 49 tokens per session scan A acc38c1adc9c
code-quality is a skill published in the GitHub repository Firstp1ck/pi-coding-agent-forge (91 stars, last pushed today), licensed MIT. It adds 82 tokens to every session and 1,783 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 89% identical to code-quality, differing in 252 lines, and is treated as a copy.
Other skills, from other repositories
hypotheses
Turns a research direction into testable hypotheses with predictions, competing explanations and the experiments that discriminate between them, including the design (controls, randomization, blocking), sample size or seed count, the pre-specified analysis, and the result that would falsify each hypothesis. Use when a…
include-test-files-that-assert-on-behavior-being-changed-in-decl
When delegating a task affected by this skill, include.
critic-gate
Full execution protocol for MODE: CRITIC-GATE -- plan critic review, revision loops, and hard stop before execution.
code-review
Comprehensive code review methodology with severity classification and confidence thresholds.
code-philosophy
Internal logic and data flow philosophy (The 5 Laws of Elegant Defense). Understand deeply to ensure code guides data naturally and prevents errors.
tech-debt-ci-review
Codex adapter for deep technical-debt and CI-stability audits. Use when asked to find test theater, flaky tests, missing or mis-scoped tests, brittle CI/toolchain behavior, structural debt blocking green PRs, or a remediation order for opencode-swarm.