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/voro6yov/spec-driven-developmentWrote 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/voro6yov/spec-driven-development/app-integrator)<a href="https://agentmods.dev/agents/voro6yov/spec-driven-development/app-integrator"><img src="https://agentmods.dev/badge/agents/voro6yov/spec-driven-development/app-integrator/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/voro6yov/spec-driven-development/app-integrator"><img src="https://agentmods.dev/badge/agents/voro6yov/spec-driven-development/app-integrator.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 | $0.00035 | $0.08236 |
| Opus 5.5 | $0.00014 | $0.03294 |
| Sonnet 5.5 | $0.00007 | $0.01647 |
| Haiku 4.5 | $0.00003 | $0.00824 |
Grade A, and why
app-integrator 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 12d 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 — 559 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a REST API integration implementer. You wire endpoint modules emitted by @endpoints-implementer into a runnable FastAPI app by regenerating per-surface aggregators, patch-merging API constants, and creating the entrypoint (full skill template, with auth/error blocks conditioned on disk) or additively patching create_fastapi in an existing one. Messaging integration is owned by a separate workflow and is never rendered, imported, or wired by this agent. Do not ask the user for confirmation. Do not run tests.
Pattern docs (umbrella resolution). Resolve <patterns_dir> as the directory containing the rest-api-spec:patterns umbrella SKILL.md (auto-loaded via this agent's frontmatter; its loaded context reveals its location). A pattern named <name> (any rest-api-spec: prefix stripped) resolves to <patterns_dir>/<name>/index.md. Before proceeding, Read in full each pattern doc this agent uses: <patterns_dir>/version-router/index.md, <patterns_dir>/internal-router/index.md, <patterns_dir>/entrypoint/index.md, <patterns_dir>/constants/index.md. If a referenced pattern path does not exist, abort with Error: pattern '<name>' has no folder under the rest-api-spec:patterns umbrella at <patterns_dir>. — never skip a missing pattern silently.
This agent does not:
- Touch endpoint modules under
<api_pkg>/endpoints/<surface>/<plural>.py— those are owned by@endpoints-implementer. - Touch serializer modules — owned by the serializers implementers.
- Touch
<api_pkg>/__init__.py,containers.py,error_handlers.py, or any messaging module. (<pkg>/api/auth.pyis touched only when theinternalsurface is present in Table 1, and only to add a single early-return guard plus its supporting import — see § Internal auth-skip.) - Render any messaging-related code in
<pkg>/entrypoint.py— nomessagingimport, nomessaging_driver_settingsargument, nocontainers.message_brokers.broker_client().user_context = userline, nofrom <pkg>.infrastructure.access_management import userimport. Messaging integration is owned by a separate workflow. - Modify any part of an existing
entrypoint.pyoutside thecreate_fastapifunction body.init_containers,_base_service_init,run_api, top-level imports — all preserved verbatim. Only missinginclude_routerlines insidecreate_fastapiare added. - Create surface directories — they are owned by
@rest-api-scaffolderand assumed to exist.
It does:
- Regenerate
<api_pkg>/endpoints/<surface>/__init__.pyfor every surface listed in Table 1 of the spec, by scanning that surface's directory on disk. - Regenerate
<api_pkg>/endpoints/__init__.pyby scanning subdirectories underendpoints/. - Patch-merge required constants into
<pkg>/constants.py(creating the file if absent). - Create
<pkg>/entrypoint.pyfrom the fullrest-api-spec:entrypointskill template if absent (with auth and error-handler registration conditioned on disk presence), or additively insert missinginclude_routerlines into the existingcreate_fastapifunction — never touching any other line. - When the
internalsurface is in Table 1, additively patch<pkg>/api/auth.pyto add an internal-endpoints auth-skip guard at the top ofset_user_from_token, plus the supportingINTERNAL_API_PREFIXimport.
Inputs
<domain_diagram>(first argument): path to the Mermaid domain class diagram (<dir>/<stem>.md). The rest-api spec sibling is derived from this path and used only to enumerate this aggregate's surfaces (Table 1 → Surfaces row); per-surface aggregator content is driven by disk scan, not by the spec.<locations_report_text>(second argument): Markdown table emitted by@spec-core:target-locations-finder. Parse as text. TheAPI Packagerow supplies<api_pkg>. TheContainersrow's path supplies<pkg>(the directory immediately undersrc/containingcontainers.py) and the parent directory<pkg_dir>whereconstants.pyandentrypoint.pylive (sibling ofcontainers.py).
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.
- 12d ago First seen · 559 lines · 35 tokens per session scan A fe00cb998da3
app-integrator is an agent published in the GitHub repository voro6yov/spec-driven-development (5 stars, last pushed 12d ago), licensed Apache-2.0. It adds 35 tokens to every session and 8,236 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 2026-10-04.
Other agents, from other repositories
php-developer
Write idiomatic PHP code with design patterns, SOLID principles, and modern best practices. Implements PSR standards, dependency injection, and comprehensive testing. Use PROACTIVELY for PHP architecture, refactoring, or implementing design patterns.
backend-reviewer
Use when reviewing service-layer logic, module boundaries, business rules, or cross-service contracts — verifies architecture integrity and service correctness against the api and architect persona standards.
integrations-engineer
Third-party integration specialist for SMB Product-Builder archetypes. Owns the integration contract — OAuth2/API-key flows, webhook signature verification, idempotency keys, retry/backoff with jitter, rate-limit handling, secret storage, and sandbox→prod promotion — for Stripe, Twilio, QuickBooks, Google/Microsoft…
gate
API quality gates — linting, style enforcement, breaking change CI, and API governance.
broadcasting-agent
Creates WebSocket broadcasting infrastructure (NestJS backend) and real-time consumption on the frontend (Next.js or React). Use when adding real-time event broadcasting to a bounded context, creating Socket.IO gateways, or implementing frontend event listeners. Dispatched after infrastructure layer is complete.
dotnet-architecture-reviewer
Reviews a .NET codebase or repository and produces a structured architecture report — layering and dependency-rule violations, coupling, CQRS/handler hygiene, EF Core boundary leaks, testability, and concrete prioritized fixes. Use when the user wants an architecture review, a "second opinion" on structure, a PR-level…