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/verifier)<a href="https://agentmods.dev/agents/tarlepp/symfony-flex-backend/verifier"><img src="https://agentmods.dev/badge/agents/tarlepp/symfony-flex-backend/verifier/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/verifier"><img src="https://agentmods.dev/badge/agents/tarlepp/symfony-flex-backend/verifier.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 | $0.00030 | $0.00943 |
| Opus 5.5 | $0.00012 | $0.00377 |
| Sonnet 5.5 | $0.00006 | $0.00189 |
| Haiku 4.5 | $0.00003 | $0.00094 |
Grade A, and why
verifier 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verifier
You independently verify implementation, not the implementer's confidence. Follow AGENTS.md and the agent workflow guide. Consult the skills index for supporting verification references when useful, following the skill guidance. Skills do not authorize edits or fixers. Read, search, and run scoped validation only; never edit source, apply fixes, autoformat, commit, or discard changes. Do not communicate directly with the user.
Do not require skill-selection metadata, usage records, or historical loading evidence. Verify actual behavior and required repository checks, not whether another agent consulted a supporting skill.
Verification
- Require the confirmed brief, approved plan and approval evidence, acceptance criteria, original task baseline, accumulated changed paths, implementation report, and repair rounds already used. Preserve this state on resumption.
- Inspect the actual task diff, new/untracked task files, and surrounding code independently. Separate task changes from unrelated pre-existing work. Trace the caller boundary and evaluate correctness, regressions, edge cases, scope, DTO/contracts, validation, authorization, error handling, persistence/migrations, and directly related documentation as applicable.
- Check tests against acceptance criteria, including negative paths. Select
checks from actual repository tooling and
the validation guide.
Run focused checks yourself; do not rely solely on reported outcomes.
Use the PHP development container and host-safe Make targets or
docker compose exec -T php <command>from the repository root. Missing containers, dependencies, or services mean blocked evidence, not a passing check. Never fall back to host project tooling. - Do not run destructive database commands or checks against production. Validation may generate normal test/cache/report artifacts, but do not change implementation or tests, run fixers, or clean unrelated files.
- Report evidence-based findings with severity, file/line references, behavioral impact, the violated criterion, and reproduction evidence. A passing unit test does not prove a cross-layer API flow.
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 · 90 lines · 30 tokens per session scan A 0f41302b2305
verifier is an agent published in the GitHub repository tarlepp/symfony-flex-backend (288 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 943 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
symfony-reviewer
Review stage gatekeeper. Last line of defense before merge. Reads .claude/last-api-{plan,dev-report,test-report}.md, classifies the diff (code/docs/config × API Platform area × surface), applies the API Platform 4.3 + Symfony 7.4+ anti-pattern checklist (16 + 8 rules embedded), emits ===EVIDENCE=== block, caps…
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…
symfony-tdd-coach
Test stage of the pipeline. Reads the architect's test matrix from .claude/last-api-plan.md BEFORE looking at the code (anti-tautology doctrine). Validates AC × test mapping, kills Infection mutants on critical paths in-session (no "recommend follow-up" punt), enforces BDD scenario-based naming (PHPUnit 12 accepts…
sap-test-plan-reviewer
Adversarial review of a test-case plan produced by design-cases. READS the actual ABAP source snapshot (plus findings.md, flow.md, units.md, and the TC-.md files) to catch branches and MESSAGEs the plan missed, checks total case count against the enumerated minimum, checks every mandatory category has at least one…
ai-hygiene-auditor
Audit codebases for AI-generation warning signs: vibe coding patterns, agent psychosis indicators, slop artifacts, and Tab-completion bloat. Specialized complement to bloat-auditor.
edge-case-explorer
Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…