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 instructions/pronskiy/php-src-developer/claude-mdgit clone --depth 1 https://github.com/pronskiy/php-src-developerWhat 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 | $0.01423 | $0.01423 |
| Opus 5 | $0.00711 | $0.00711 |
| Sonnet 5 | $0.00285 | $0.00285 |
| Haiku 4.5 | $0.00142 | $0.00142 |
Grade A, and why
php-src-developer CLAUDE.md 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
php-core-developer
Claude Code plugin for developing the PHP language core (php/php-src).
Execution model
One agent (php-core-dev), eight skills, one living document per task. Each step is one slash command run by the user.
| Workflow | Living doc | Skills (run in order) |
|---|---|---|
| Bug fix | SPEC.md |
/bug-context <gh-issue> → /research → /bug-reproduce-test → /bug-fix → /bug-verify |
| Upmerge (after a bug fix on a non-master branch) | UPMERGE.md |
/upmerge (dry-run) → /upmerge --execute |
| Idea prototype | SPEC.md |
/idea-prototype "<one-line hypothesis>" (advances Context → Hypothesis & Metric) → /research (Research phase) → /idea-prototype (Survey & Plan → Prototype → Verdict) |
| Code review (local) | REVIEW.md |
/review-local [base-ref] |
| Code review (PR) | REVIEW.md |
/review-pr <pr-number> |
/research gating differs by flow:
- Bug fix: soft-gated.
/bug-reproduce-test//bug-fix//bug-verifywarn if Research istodobut proceed anyway. - Idea prototype: hard-gated.
/idea-prototyperefuses to advance past Hypothesis & Metric until Research isdoneor explicitlyskippedin SPEC.md. Prior-art sweeps catch declined RFCs and abandoned attempts that would otherwise waste a prototype.
Mark the phase skipped in SPEC.md (with reason) to bypass either gate.
SPEC.md is the state
For bug and idea workflows the entire task state lives in SPEC.md in the working directory. It's organised as Phase → Step → Guardrail:
- A phase is a top-level workflow stage (Context, Reproduction, Analysis & Plan, …).
- A step is a concrete action with its own status (
todo/in-progress/done/skipped/blocked). - A guardrail is a pre- or post-condition gated against a step. Pre-guardrail fails → skill refuses to start; post-guardrail fails → step marked
blocked.
Each skill on every invocation: read SPEC.md, find the first non-done phase / step, run pre-guardrails, do the work, run post-guardrails, mark done, append one line to the Progress Log. Close the terminal mid-phase; the next slash command resumes from there.
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 · 93 lines · 1,423 tokens per session scan A a785b2286901
php-src-developer CLAUDE.md is an instructions file published in the GitHub repository pronskiy/php-src-developer (8 stars, last pushed 3mo ago), licensed MIT. It adds 1,423 tokens to every session, about $0.0071 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 instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.