Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Kin9Zeus/senior-engineer-skillsnpx agentmods add commands/kin9zeus/senior-engineer-skills/snr-phpWrote 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/commands/kin9zeus/senior-engineer-skills/snr-php)<a href="https://agentmods.dev/commands/kin9zeus/senior-engineer-skills/snr-php"><img src="https://agentmods.dev/badge/commands/kin9zeus/senior-engineer-skills/snr-php/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/commands/kin9zeus/senior-engineer-skills/snr-php"><img src="https://agentmods.dev/badge/commands/kin9zeus/senior-engineer-skills/snr-php.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 | $0.00034 | $0.00559 |
| Opus 5.5 | $0.00014 | $0.00224 |
| Sonnet 5.5 | $0.00007 | $0.00112 |
| Haiku 4.5 | $0.00003 | $0.00056 |
Grade A, and why
snr-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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PHP Security Pass
Scope: $ARGUMENTS (default: the whole repository and its deployment config).
Load the php-hardening skill. Defensive only. Do not trust remembered versions
or CVEs — the incident facts in the skill are dated 2026-10-23; re-read the
official PHP advisory and your distribution's tracker before asserting anything.
1 · Run the inventory
bash skills/php-hardening/scripts/php-check.sh . # PowerShell: php-check.ps1
Every hit is a lead. Then answer from the real environment, not the repo:
- Which PHP actually serves requests? (FPM / Apache
mod_php/ container / platform build) - Is it at or above the fixed release for its branch, or a vendor-fixed build?
- Were all workers restarted after patching? Is the running build verified?
2 · If anything is unpatched
Follow references/php2shell-response.md: patch → restart → verify; interim
mitigations only if patching must wait (each with owner and removal date);
edge restrictions; then the compromise assessment — assume exposure for the
window since 17 October 2026, rotate secrets the PHP process could read, and hunt
(security-incident-response). If the platform also reported a secrets incident,
treat both as one.
3 · Then harden
In yield order: supported branch with a patch SLA → PHP-FPM over mod_php and a
pool per app → baseline config (references/php-ini-baseline.md) → least-privilege
process and container → application code (references/php-code-security.md) →
Composer / WordPress / Laravel / Symfony hygiene (references/php-ecosystem.md).
4 · Output
Findings in the suite format (what is wrong → why it matters → fix → verify), P0 first:
### <Title> — P0
**Class** · **Location** · **Confidence** CONFIRMED | PLAUSIBLE · **Impact** ·
**Reproduce/Evidence** · **Fix** · **Verify**
For code findings, include a failing regression test. End with What I could not verify — typically the serving SAPI, the real running build, and distro backports.
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 · 54 lines · 34 tokens per session scan A 886fb8cbf320
snr-php is a command published in the GitHub repository Kin9Zeus/senior-engineer-skills (3 stars, last pushed 2d ago), licensed MIT. It adds 34 tokens to every session and 559 once invoked, about $0.0001 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 2026-10-24.
Other commands, from other repositories
profile
Coordinate a reproducible Java profiling and optimization lifecycle.
generate-idl-client
Generate a typed client from an Anchor or Shank IDL (Codama or Anchor TS).
adr
Write an architecture decision record as Markdown in the user's repository. Use when invoked as /document-design-system:adr. Produce designed HTML or PDF only when asked.
support-model
Write a support model as Markdown in the user's repository. Produce designed HTML or PDF only when asked.
laravel
Laravel development with Eloquent, Blade, Livewire, queues, and Pest testing.
infolist
Create FilamentPHP v4 infolists with entries, layouts, and sections for read-only view pages.