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.
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.
curl -O https://raw.githubusercontent.com/symfony/ai-demo/main/.agents/skills/mate-symfony-log-investigation/SKILL.mdgit clone --depth 1 https://github.com/symfony/ai-demoWrote 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/skills/symfony/ai-demo/mate-symfony-log-investigation)<a href="https://agentmods.dev/skills/symfony/ai-demo/mate-symfony-log-investigation"><img src="https://agentmods.dev/badge/skills/symfony/ai-demo/mate-symfony-log-investigation/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/skills/symfony/ai-demo/mate-symfony-log-investigation"><img src="https://agentmods.dev/badge/skills/symfony/ai-demo/mate-symfony-log-investigation.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 | $0.00074 | $0.00960 |
| Opus 5.5 | $0.00030 | $0.00384 |
| Sonnet 5.5 | $0.00015 | $0.00192 |
| Haiku 4.5 | $0.00007 | $0.00096 |
Grade A, and why
mate-symfony-log-investigation 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 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.
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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Log investigation
Reads Monolog files through Mate's CLI. Entries come back as {datetime, channel, level, message, context, extra, source_file, line_number}. Sensitive context keys are redacted in the output but still matched when you search them.
monolog-list-files(optenvironment): what log files exist, newest first.monolog-list-channels: distinct channel names (app,security,doctrine, ...). Reads every file, so it is the slow one; skip it if you already know the channel.monolog-tail(limit,level,environment,channel): most recent entries. Reads ONLY the single newest file.monolog-search(term,regex,level,channel,environment,from,to,limit): searches across all files.termis optional; omit it (or pass an empty string) to filter bylevel/channel/from/toonly, e.g. "just show me the errors".monolog-context-search(key,value,level,environment,limit): matches a structured context field. No channel or date filter here.
These commands accept --format: json to parse the result, toon (when helgesverre/toon is installed) for the smallest context footprint. A wide search returns many entries, so narrow with filters and a limit before widening the output format.
Workflow
- Orient:
vendor/bin/mate tools:call monolog-list-files. Confirm the environment you care about is present and recently modified. - Latest state:
vendor/bin/mate tools:call monolog-tail --level=error --limit=50. Good for "what just broke", nothing else. - Narrow with search:
vendor/bin/mate tools:call monolog-search --term="Timeout" --level=error- Time-box it:
--from="-1 hour",--from=2026-07-01 --to=2026-07-02. Any PHP-parseable date works. - Regex:
vendor/bin/mate tools:call monolog-search --term="user \d+ locked" --regex. A bare pattern is wrapped as/.../i; pass your own/.../or#...#to control anchoring and flags.
- Pivot on a field: once you have an identifier (request id, user id, order id), follow it with
vendor/bin/mate tools:call monolog-context-search --key=request_id --value=abc123. This is how you reconstruct one request or one user across many lines.
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.
- 1mo ago First seen · 40 lines · 74 tokens per session scan A 229be1052f57
mate-symfony-log-investigation is a skill published in the GitHub repository symfony/ai-demo (48 stars, last pushed 2d ago), licensed MIT. It adds 74 tokens to every session and 960 once invoked, about $0.0003 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 2026-09-25.
Other skills, from other repositories
system-information
Resolve which dependency versions are actually installed, from composer show and composer.lock, when diagnosing version-specific behavior such as a method, argument or class that does not exist in the release that is really running. For the PHP runtime itself (version, OS, loaded extensions) use the…
php-environment-check
Check the PHP runtime with server-info, its version, OS, and loaded extensions. Reach for it when a Mate tool itself fails or a capability is missing and you suspect the environment, a missing extension or an old PHP, rather than the app or its config. Not for diagnosing app behavior (profiler, log investigation) or…
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
agent-merge-conflict-arbiter
Neutral arbiter for merge conflicts between two agents.
triage-issues
Triage GitHub issues in the googleapis/mcp-toolbox repo: propose the correct labels (type / priority / product / status), check for duplicates, verify a bug has enough info to act on, and draft a triage comment. Use whenever a maintainer asks you to triage, label, categorize, prioritize, or "look at" an issue (or a…
python-debugpy
Debug Python: pdb REPL + debugpy remote (DAP).