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 hmj1026/dhpk --skill yii1git clone --depth 1 https://github.com/hmj1026/dhpkWrote 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/hmj1026/dhpk/yii1)<a href="https://agentmods.dev/skills/hmj1026/dhpk/yii1"><img src="https://agentmods.dev/badge/skills/hmj1026/dhpk/yii1/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/hmj1026/dhpk/yii1"><img src="https://agentmods.dev/badge/skills/hmj1026/dhpk/yii1.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 | $0.00072 | $0.00936 |
| Opus 5.5 | $0.00029 | $0.00374 |
| Sonnet 5.5 | $0.00014 | $0.00187 |
| Haiku 4.5 | $0.00007 | $0.00094 |
Grade A, and why
yii1 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 yesterday.
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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Yii1
Use $yii1 <task>; natural development, review, and security requests select
internal procedures. PHP language/runtime ownership remains with php; this
family owns Yii1.1 framework behavior and its runtime-compatible adaptations.
It needs no peer skill to complete a scoped Yii task.
Establish the target before loading
Identify the application/subproject, Yii version, PHP deployment floor and
configured test runner from request and entrypoint/manifest/configuration
facts. An intentional explicit version override wins; retain its rationale.
Yii::createWebApplication, protected controllers/models/views, CController or
CActiveRecord, and components configuration are framework evidence. Yii2 is
outside this family. A missing/ambiguous target, broad incompatible ranges or
conflicting evidence requires asking and waiting before framework/version
references or dependent actions. Local php --version describes the execution
environment. Migration needs an explicit destination; group multiple targets
and evidence separately. Never infer PHP5.6 just from Yii1 identity; preserve
PHP5.6 compatibility when the target requires it.
Select the procedure
- Implementation, known bugfix, refactor, or hardening: read development, then only the needed backend, DDD-lite, compatibility, TDD, or legacy-test references it selects.
- Static framework-security audit: read security and patterns. Establish at least three Yii1.1 identity evidence points before auditing; insufficient evidence stops the audit with its cause. Review all eight checklist categories.
- An ordinary code review uses development's findings output. Security-specific evidence uses the audit procedure; do not automatically load both procedures.
Read local references from this folder. Context7 is an external knowledge
capability for uncertain APIs, not a required bundled resource. The local
source/query rules preserve
provenance and inference reporting; unavailable sources stay disclosed rather
than fabricated. Missing local references are BLOCKED and cannot be recovered
from predecessors or ambient repository modules.
What ships with it
12 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.
- agents/openai.yaml 221 B
- distribution.yaml 1.9 KB
- evals/evals.json 3.3 KB
- references/context7-sources-and-query-rules.md 2.6 KB
- references/ddd-lite-for-yii1.md 2.2 KB
- references/development.md 7.1 KB
- references/php56-php7-safe-subset.md 2.4 KB
- references/phpunit57-legacy-test-traps.md 2.4 KB
- references/security.md 9.0 KB
- references/tdd-workflow-and-test-strategy.md 2.4 KB
- references/yii1-backend-patterns.md 2.7 KB
- references/yii1-security-patterns.md 11 KB
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.
- yesterday First seen · 79 lines · 72 tokens per session scan A b39a674e1ccb
yii1 is a skill published in the GitHub repository hmj1026/dhpk (2 stars, last pushed today), licensed MIT. It adds 72 tokens to every session and 936 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 2026-10-16.
Other skills, from other repositories
list-connections
Lists Power Platform connections in the current environment. Use when you need a connection ID before adding a connector to a code app.
bun-http-server
Use when building HTTP servers with Bun.serve, handling requests/responses, implementing routing, creating REST APIs, or configuring fetch handlers.
craft-content-modeling
Craft CMS 5 content modeling — sections, entry types, fields, Matrix, relations, project config, and content architecture strategy. Covers choosing section types, designing entry types and field layouts, selecting field types, configuring Matrix and nested entries, relations and eager loading, and multi-site…
outsystems-spec-driven-build
Beta Feature. This skill is a Beta Feature: a non-final OutSystems capability provided to collect customer feedback. It can change significantly, including through breaking changes, or be discontinued. The first time you use this skill in a conversation, tell the user it's a Beta Feature and share .
verify
Drive/evidence recipe for verifying wenlan changes at their real surfaces (daemon HTTP, CLI, MCP stdio). The handle file the built-in verify protocol expects; launch primitives live in the run-wenlan skill, deeper machinery (mutation audit, behavior trace, weekly sweep) in the prove skill.
python-patterns
Python backend patterns: layered architecture, async I/O, dependency injection, repository/service separation. TRIGGER when: creating routes, models, schemas, or services in a Python backend. SKIP: REST contract design (use api-design); schema/index tuning (use database-optimization). (Examples: FastAPI + SQLAlchemy +…