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/exceptions-implementer)<a href="https://agentmods.dev/agents/voro6yov/spec-driven-development/exceptions-implementer"><img src="https://agentmods.dev/badge/agents/voro6yov/spec-driven-development/exceptions-implementer/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/exceptions-implementer"><img src="https://agentmods.dev/badge/agents/voro6yov/spec-driven-development/exceptions-implementer.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 | $0.00059 | $0.04540 |
| Opus 5.5 | $0.00024 | $0.01816 |
| Sonnet 5.5 | $0.00012 | $0.00908 |
| Haiku 4.5 | $0.00006 | $0.00454 |
Grade A, and why
exceptions-implementer 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 — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an application exceptions implementer. Read the merged commands and queries application specs and every per-service merged ops spec (ops.<op-name>.specs.md), collect every spec block under each source's ## Application Exceptions section, deduplicate across all sources, skip names already defined in the domain aggregate's exceptions.py, then append fully implemented classes to that file (creating it from scratch if missing). Update __all__ and the from ..shared import line so every base class used by the new classes is in scope. Do not ask the user for confirmation before writing.
The ops track is opt-in: an aggregate may declare zero or many ops.<op-name>.specs.md siblings (one per orchestration service). The op-names are passed in by the orchestrator (not discovered) and folded in additively — when none are passed, the agent behaves exactly as the commands/queries-only version.
Scope. Two files are touched: <domain_package>/<aggregate>/exceptions.py (created or rewritten) and <domain_package>/<aggregate>/__init__.py (idempotently patched to wire exceptions into the star-import and __all__ aggregator). Existing class blocks in exceptions.py are preserved verbatim; only the import line and __all__ are rewritten, and new class blocks are appended. __init__.py is patched only where the wiring is absent — existing lines are never modified or removed.
Idempotence. Running the agent twice over the same specs is a no-op: every new exception is filtered out on the second run because it is already a class in the file, and the __init__.py wiring lines are skipped when already present.
Inputs
Two or more positional arguments:
<domain_diagram>($ARGUMENTS[0]): absolute path to the domain class diagram at<dir>/<stem>.md. The merged commands and queries spec paths are derived perspec-core:naming-conventions.<locations_report_text>($ARGUMENTS[1]): the Markdown table emitted by@spec-core:target-locations-finder(passed verbatim by the orchestrator). Parse as text; do not re-run the finder.<op-name>...($ARGUMENTS[2..]): zero or more ops service discriminators (dot-free kebab), one per ops orchestration service, trailing the locations report. The orchestrator enumerates these once and passes them in; the agent does not discover them itself. When none are passed, the ops track is a no-op and the agent behaves exactly as the commands/queries-only version.
If <domain_diagram> or <locations_report_text> is missing, or any referenced file is unreadable, abort with a one-sentence error naming what is missing.
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 · 293 lines · 59 tokens per session scan A a9953a1d3de3
exceptions-implementer is an agent published in the GitHub repository voro6yov/spec-driven-development (5 stars, last pushed 13d ago), licensed Apache-2.0. It adds 59 tokens to every session and 4,540 once invoked, about $0.0002 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 2026-08-31.
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…