ai-demo: Skill for Claude Code

.agents/skills/mate-symfony-profiler-debugging/SKILL.md

mate-symfony-profiler-debugging is a skill for Claude Code, Codex from symfony/ai-demo. It costs 71 tokens per session (1,048 once invoked), scanned A, original, MIT.

A Symfony request debugging tool that reads the Symfony profiler, which records detailed information about a web request. It finds a failed, slow, or otherwise problematic request and then examines the data collected for that request.

In plain words
What is it for?
Use it to find requests by URL, status, time, or other filters, then inspect available profiler sections such as request, database, or performance details.
Why use it?
It avoids searching through unrelated profiler records and helps investigate one known request rather than guessing from application behavior.

Skill for Claude CodeCodex ✓ vendor

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is symfony/ai-demo's own configuration. It tells Claude Code and Codex how to work on ai-demo itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-demo configures →

About the project

Symfony AI Demo is a Symfony application that demonstrates AI components through a chatbot using OpenAI language and embedding models, with PostgreSQL and pgvector storing contextual embeddings. Developers use it to explore a Symfony-based AI application and its setup.

symfony/ai-demo · 48 stars · on GitHub · symfony.com

Reuse

Borrowing it

Nothing to install: this file belongs to symfony/ai-demo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/symfony/ai-demo/main/.agents/skills/mate-symfony-profiler-debugging/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/symfony/ai-demo

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for mate-symfony-profiler-debugging

README.md
[![agentmods](https://agentmods.dev/badge/skills/symfony/ai-demo/mate-symfony-profiler-debugging/github.svg)](https://agentmods.dev/skills/symfony/ai-demo/mate-symfony-profiler-debugging)
Your own site
<a href="https://agentmods.dev/skills/symfony/ai-demo/mate-symfony-profiler-debugging"><img src="https://agentmods.dev/badge/skills/symfony/ai-demo/mate-symfony-profiler-debugging/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.

agentmods 80×15 button for mate-symfony-profiler-debugging

Your own site · 80×15
<a href="https://agentmods.dev/skills/symfony/ai-demo/mate-symfony-profiler-debugging"><img src="https://agentmods.dev/badge/skills/symfony/ai-demo/mate-symfony-profiler-debugging.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,048 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00071 $0.01048
Opus 5.5 $0.00028 $0.00419
Sonnet 5.5 $0.00014 $0.00210
Haiku 4.5 $0.00007 $0.00105

Measured 1mo ago against content hash 0ec3a0cd7955, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mate-symfony-profiler-debugging scanned grade A with 1 finding 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 1mo 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

`summary` has `method`, `path`, `route`, `status_code`, `content_type`. `data` has the sanitized bags (`request_query`, `request_request`, `request_headers`, `session_attributes`). Sensitive values, the raw body, and the
.agents/skills/mate-symfony-profiler-debugging/SKILL.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Profiler debugging

Reads the profiler through Mate's CLI. Two tools, two resources:

  • symfony-profiler-list filters profiles (method, url, ip, statusCode, context, from, to, limit). Newest first, so --limit=1 is the latest. Returns summaries with a resource_uri per profile.
  • symfony-profiler-get --token=<t> returns one profile's metadata. It does NOT list collectors.
  • symfony-profiler://profile/{token} lists the collectors this profile actually has, each with its URI.
  • symfony-profiler://profile/{token}/{collector} returns that collector, as {name, data, summary}. summary is the triage view, data the full detail.

These commands accept --format: json to parse the result, toon (when helgesverre/toon is installed) for the smallest context footprint. On a large profile, prefer one of these over the human-readable default.

Workflow

  1. Find the profile. Do not scroll all profiles.
    • Error: vendor/bin/mate tools:call symfony-profiler-list --statusCode=500 --limit=5
    • Known URL: --url=/checkout. Latest request: --limit=1.
  2. vendor/bin/mate resources:read symfony-profiler://profile/<token> to see which collectors exist. Apps differ; only read what is present.
  3. Read collectors in diagnosis order, not all of them.

Reading order

Branch on the symptom.

Errored (5xx / exception): read exception first. data.class, message (secrets scrubbed), file, line, and trace (top 10 frames) are the fix. If has_exception is false on an error response, the failure is upstream: check request for the status and logger for what was logged.

Slow but succeeded: skip exception, go to time, then db, then memory.

  • time: duration_ms is total. events are sorted slowest first with a category (e.g. doctrine, template, controller) that tells you which subsystem ate the time. That category picks the next collector.
  • db: query_count plus summary.duplicate_query_count. queries are grouped by identical SQL, sorted by total_time_ms. An N+1 shows as one grouped entry with a high count (same statement fired in a loop), or a high duplicate_query_count. One slow statement shows as a high avg_time_ms. sample_params shows what was bound. Grouped list caps at 50 (queries_truncated).
  • memory: usage_percent against the limit. Only relevant when the request is heavy or OOMs.

Read the full file on GitHub · 50 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. 1mo ago First seen · 50 lines · 71 tokens per session scan A 0ec3a0cd7955

Subscribe to this mod's changes

mate-symfony-profiler-debugging is a skill published in the GitHub repository symfony/ai-demo (48 stars, last pushed 2d ago), licensed MIT. It adds 71 tokens to every session and 1,048 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-25.