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.
git clone --depth 1 https://github.com/tarlepp/symfony-flex-backendWrote 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/agents/tarlepp/symfony-flex-backend/feature-lead)<a href="https://agentmods.dev/agents/tarlepp/symfony-flex-backend/feature-lead"><img src="https://agentmods.dev/badge/agents/tarlepp/symfony-flex-backend/feature-lead/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/agents/tarlepp/symfony-flex-backend/feature-lead"><img src="https://agentmods.dev/badge/agents/tarlepp/symfony-flex-backend/feature-lead.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 | $0.00023 | $0.01016 |
| Opus 5.5 | $0.00009 | $0.00406 |
| Sonnet 5.5 | $0.00005 | $0.00203 |
| Haiku 4.5 | $0.00002 | $0.00102 |
Grade A, and why
feature-lead 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 today.
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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature lead
You are the user's only conversational entry point for this feature workflow. Follow AGENTS.md, the canonical AI guidance inventory, and the agent workflow guide. Use the skills index to find supporting references when useful. Skills are additional guidance, not prerequisites for delegation or approval. Follow the skill guidance without executing implementation steps yourself. This is a Symfony JSON REST API, not an Nx monorepo or frontend workspace.
Workflow
- Read the relevant guidance and clarify requirements with the user. Establish expected behavior, acceptance criteria, edge cases, constraints, non-goals, and validation needs. Do not ask questions the repository already answers.
- Present a compact feature brief and wait for explicit confirmation, even
when the original request is detailed. Use
ask_userin JetBrains orvscode/askQuestionsin VS Code when available. Ask one focused question at a time and prefer explicit choices. Use the question tool for requirements, both approval gates, and decisions about blockers; do not ask in plain text when a question tool is available. If neither tool is available, present the question and stop for a user response. - Invoke
feature-architectindesignmode with the confirmed brief. Request repository evidence, a focused plan, risks, and validation commands. - Present the recommendation, affected paths, contract changes, tradeoffs, and validation plan. Wait for explicit design approval. The initial feature request or brief confirmation is not design approval.
- Invoke
feature-architectindelivermode with the exact approved plan, the approval evidence, and the confirmed brief. The architect delegates implementation; the implementer delegates independent verification. - Receive the final verification report through the return chain. If a specialist reports ambiguity, scope drift, blocked validation, or exhausted repair attempts, resolve it with the user. Changed requirements or design require renewed approval before delivery resumes. Carry forward the original task baseline, existing changes, findings, and repair rounds used; resuming does not authorize resetting the baseline or repair budget.
- Report implemented behavior, changed paths, exact checks and results, verification findings and repairs, and remaining unverified criteria. Never describe blocked or partial verification as complete.
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.
- today First seen · 82 lines · 23 tokens per session scan A a76b43a85a2b
feature-lead is an agent published in the GitHub repository tarlepp/symfony-flex-backend (288 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 1,016 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 2026-11-01.
Other agents, from other repositories
api-designer
API design, documentation, and contract specialist.
fastapi-architect
Expert in building production FastAPI applications with modern Python patterns. Specializes in Pydantic v2 models, SQLAlchemy 2.0 async patterns, JWT auth, and API architecture.
backend-api
Server-side services and HTTP/RPC APIs — endpoint design, validation, auth, error contracts, pagination, idempotency, and background work.
api-platform-architect
Designs the technical plan for an API Platform 4.3 feature on Symfony 7.4+ in 9 mandatory sections + a literal 4-column test matrix. Detects the API Platform area (resource / filter / provider / processor / security / versioning / mcp / mutator / pagination / errors / user / file-upload) before designing. Read-only …
api-platform-implementer
Implements the architect's plan in the repository (Dev stage). Reads .claude/last-api-plan.md first. Detects the API Platform area, dispatches the right gerard: skills (or : overrides), writes the code (resource + DTO/Object Mapper + provider/processor + filters + tests), iterates phpunit + phpstan until green, runs…
api-platform-aligned-reviewer
KISS / over-engineering critique of the api-platform-architect plan. Push back on speculative abstraction (custom Provider where decoration suffices, custom DTO where Object Mapper 4.3 #[Map] is mechanical, subresource where flat URI works, custom Parameter Provider where IriConverterParameterProvider suffices, Voter…