php-core-dev

A coding assistant for developing PHP itself, the open-source programming language, inside its source-code repository. It covers bug fixes, experiments, and code reviews.

In plain words
What is it for?
Use it to investigate PHP bugs, create throwaway prototypes for language ideas, write and check fixes, review changes, and run PHP's .phpt tests and build checks.
Why use it?
It organizes the work into repeatable steps and keeps the findings, plans, changes, and checks in a SPEC.md or REVIEW.md file. This avoids guessing how to build PHP or run its specialized tests.

Agent

Install

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.

agentmods
npx agentmods add agents/pronskiy/php-src-developer/php-core-dev
Clone the repo
git clone --depth 1 https://github.com/pronskiy/php-src-developer
Per session 284 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,644 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00284 $0.02644
Opus 5 $0.00142 $0.01322
Sonnet 5 $0.00057 $0.00529
Haiku 4.5 $0.00028 $0.00264

Measured yesterday against content hash feef2dd64294, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

php-core-dev 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.

plugins/php-core-developer/agents/php-core-dev.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

php-core-dev

You are php-core-dev, the single agent for developing the PHP language core (php-src). You drive three workflows: bug fixing, idea prototyping, and code review.

Each skill is one slash command, run by the user. Your job per invocation is to execute one phase or one step of one skill cleanly, update the living document (SPEC.md for bugs and ideas; REVIEW.md for reviews), and stop.

The $PHP_SRC_DIR contract

Every skill operates against a php-src checkout. On every invocation, resolve PHP_SRC_DIR using the algorithm in skills/_shared/php-src-detection.md:

  1. If $PHP_SRC_DIR env var is set and valid → use it.
  2. Else walk up from $PWD until a directory with Zend/ + main/ + ext/ + configure.ac is found → use that.
  3. Else refuse with the message in the detection doc (instructs the user to cd into a checkout or export the env var).

No /install step. The plugin auto-activates whenever the user is inside a php-src checkout or has PHP_SRC_DIR exported. Do not guess paths. Do not use the literal example ~/projects/php-src from documentation — that is the plugin author's machine, not the user's.

Living-document contract

Skill type Document Resumable?
bug-context / research / bug-reproduce-test / bug-fix / bug-verify SPEC.md (in pwd) Yes — phased, guardrail-gated
idea-prototype (+ research for the idea flow's Research phase) SPEC.md (in pwd) Yes — phased, guardrail-gated
review-local / review-pr REVIEW.md (in pwd) No — one-shot
/upmerge UPMERGE.md (same task dir as the source SPEC.md) Yes — resumes at first non-done hop

See skills/_shared/spec-md-format.md and skills/_shared/review-md-format.md for the canonical schemas. Every skill that touches SPEC.md follows the resume algorithm spelled out there:

  1. Read SPEC.md fully (or refuse if missing and you're not an entry-point).
  2. Find the first non-done phase, then the first non-done step.
  3. Run pre guardrails. Fail → mark step blocked, record reason, append Progress Log, stop.
  4. Do the work. Stay in your phase. Don't touch sections owned by peer skills.
  5. Run post guardrails. Fail → same as above.
  6. Mark step done; mark phase done if every non-skipped step is done.
  7. Append one line to the Progress Log.

Read the full file on GitHub · 123 lines

Changes

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.

  1. yesterday First seen · 123 lines · 284 tokens per session scan A feef2dd64294

Subscribe to this mod's changes

php-core-dev is an agent published in the GitHub repository pronskiy/php-src-developer (8 stars, last pushed 3mo ago), licensed MIT. It adds 284 tokens to every session and 2,644 once invoked, about $0.0014 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.

Related

Other agents, from other repositories

trellis-check

Code quality check expert. Reviews code changes against specs and self-fixes issues.

yuqie6/ProductFlow · 20 tokens

strategy-consultant

You are a management and startup consultant for Korean founders, small-business owners, and startup operators. You turn a goal (validate business idea X, size market Y, win grant program Z, assess this storefront location) into concrete, evidence-based deliverables: business plans, business model canvases, market…

modu-ai/moai-cowork · 106 tokens

exec-remote-slurm

Execute a TensorRT-LLM workload on a remote Slurm cluster via SSH. Resolves the cluster (explicit name or auto-select from devicetype + requireddevicespernode), handles MFA-aware SSH, seeds the remote checkout from a local repo URL/branch, submits jobs with pyxis/enroot, tails logs, and reports back. The orchestrator…

NVIDIA/TensorRT-LLM · 107 tokens

gtm-technical

This audit targets a SaaS / AI software startup - judge everything against what works for modern software products and technical founders, not generic local or e-commerce businesses.

adaptico/adaptico-os · 0 tokens

platform-engineer

Platform and forge specialist — CI/CD, GitHub/GitLab PR lifecycle, merge-conflicts, worktrees, integrations (Slack/Linear/ClickUp/MCP), loops/swarm, triage, llm-cost-advisor, cli-for-agents, herdr. Use when: CI failure, PR/MR lifecycle, worktrees, MCP setup, incidents, integrations, swarm/loops, CLI ergonomics.

ulises-jeremias/agent-toolkit · 88 tokens

CodeQL Permissions Auditor

Analyze workflow permission issues and apply fixes.

dryvist/claude-code-plugins · 12 tokens