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 agentmods add skills/soulcodex/agentic/code-review-phpnpx skills add soulcodex/agentic --skill code-review-phpgit clone --depth 1 https://github.com/soulcodex/agenticWhat 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 | $0.00066 | $0.00805 |
| Opus 5 | $0.00033 | $0.00402 |
| Sonnet 5 | $0.00013 | $0.00161 |
| Haiku 4.5 | $0.00007 | $0.00081 |
Grade A, and why
code-review-php 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 2d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review — PHP
Apply PHP-specific linting using the checklist in this skill directory.
Step 0 — Load Project Map
Check for .agentic/project-map.md:
- If present: read it. Use the layer structure, key modules table, and non-obvious conventions it defines to orient all findings. Skip redundant filesystem exploration.
- If absent: run lightweight auto-discovery:
- Read
composer.jsonto identify dependencies and namespace - Detect framework (Symfony, Laravel, etc.) from dependencies
- List top-level
src/directories - Suggest running the
project-mapskill after this review to avoid this overhead next time
- Read
Step 1 — Load Checklist
Read checklist.md in this skill directory and apply every item to the codebase.
Step 2 — Determine Scope
- If the user specifies files, review those.
- Otherwise review the current diff:
git diff HEADor staged changes. - Do not review files outside stated scope.
Step 3 — Analyze with PHP-specific Lenses
Work through the checklist systematically. For each issue found, note:
- File path and line number
- Risk level:
critical/high/medium/low - Description of the issue
- Why it matters
- Verifiable source reference when the finding is non-obvious
Focus particularly on:
- Strict type declarations
- PHPStan level 8 compliance
- PSR coding standards
- Domain/ORM boundary violations
- Enum usage (PHP 8.1+)
Step 4 — Write the Review
Output the review in this exact format:
## Code Review — PHP
### What Works Well
- [At least one specific positive observation with file reference]
### Findings
#### Critical
- `path/to/file.php:42` [critical] Description. Why it must change. *Source: [PHP Manual — strict_types](https://www.php.net/manual/en/language.types.declarations.php#language.types.declarations.strict)*
#### High
- `path/to/file.php:18` [high] Description. Why it matters. *Source: ...*
#### Medium
- `path/to/file.php:7` [medium] Description.
#### Low
- `path/to/file.php:5` [low] Minor note.
### Suggested Improvements
[Concrete alternatives and solutions for the most impactful findings]
### Summary
[One paragraph: overall quality, main risks, merge recommendation]
What ships with it
1 file 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.
- 2d ago First seen · 105 lines · 66 tokens per session scan A 2884fd061a53
code-review-php is a skill published in the GitHub repository soulcodex/agentic (10 stars, last pushed 2d ago), licensed MIT. It adds 66 tokens to every session and 805 once invoked, about $0.0003 per session on Opus 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
plugin-review
Review plugin quality with tiered checks and dependency scoping. Use for PR and pre-release audits.
critical-review
Radical-honesty architectural review — questions code, methodology, design, and operational fitness.
comprehensive-code-review
Use when performing code review on a PR, reviewing code changes before merge, or when a GitHub code review is requested or received - orchestrates parallel sub-agents for correctness and safety review.
code-review
AI-powered code review and PR analysis. Performs systematic reviews covering security vulnerabilities, code quality, style compliance, architectural integrity, test coverage, and performance considerations. Works with PR diffs, commit ranges, file changes, or raw code snippets. Primary keyword clusters: AI code review…
code-review
Comprehensive code review for security, performance, and best practices.
review-orchestrator
Get multiple perspectives on your work — coordinate reviews across cognitive modes.