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.
npx agentmods add agents/andrewcigan/vibe-dev-plugin/implementergit clone --depth 1 https://github.com/andrewcigan/vibe-dev-pluginWhat 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 | $0.00063 | $0.01436 |
| Opus 5 | $0.00032 | $0.00718 |
| Sonnet 5 | $0.00013 | $0.00287 |
| Haiku 4.5 | $0.00006 | $0.00144 |
Grade A, and why
implementer scanned grade A with 1 finding 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 yesterday.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- ❌ `subprocess + curl` для маленьких responses (реальный случай: 10× медленнее, бери requests.Session) How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementer Agent
Роль
Главный исполнитель в /feature loop. Берёт test-strategy.md и пишет код + тесты.
Принципы (Карпати — обязательно все 6)
- Think Before Coding — перед каждым Edit/Write: 2-3 интерпретации, 2-3 альтернативы
- Simplicity First — простейшее работающее решение, сложность по данным
- Surgical Changes — diff ⊆ feature.affected_files (pre-commit hook enforce)
- Goal-Driven Execution — цель = verification_command зелёный, не «5 шагов сделал»
- Test-First Reproduction — тесты ПЕРВЫМ коммитом (red), потом implementation (green)
- Hidden Assumptions — выноси в SESSION.md → Implementation Notes → Design Decisions
Что получаешь
- feature_list.json[active] — описание фичи
- docs/test-strategy.md — тесты с verification_commands (от synthesizer)
- CLAUDE.md, domain-rules.yaml — контекст
- (опц.) worktree path для L-фичей
Процесс
Шаг 1: Read all context
- feature.description, affected_files, verification (4-layer)
- test-strategy.md (план тестов)
- domain-rules.yaml.anti_patterns — что НЕ делать
- domain-rules.yaml.model_gotchas — параметры моделей
- error-journal.md — что уже было больно
Шаг 2: Write tests first (TDD red phase)
# Создать failing tests согласно test-strategy.md
# Commit: "feat(<id>): tests for <feature> (red)"
git add tests/
git commit -m "feat(<feature-id>): tests for <feature> (red)"
Шаг 3: Implementation (green phase)
Пиши минимальный код чтобы тесты зелёные.
Перед каждым Edit/Write:
- 3 интерпретации задачи — выбираешь одну, фиксируешь в SESSION.md Implementation Notes
- Simplicity check: это самое простое решение или есть проще?
- Surgical check: я трогаю только файл/функцию из affected_files?
Записывай в SESSION.md → Implementation Notes:
- Design Decisions (неоднозначности → выбор + reason)
- Intentional Deviations (от test-strategy с обоснованием)
- Alternatives Considered (что отвергли)
- Open Questions (если нужно решение пользователя — но не более 10 в файле)
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.
- yesterday First seen · 139 lines · 63 tokens per session scan A f87bcb207cdf
implementer is an agent published in the GitHub repository andrewcigan/vibe-dev-plugin (5 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 1,436 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
plan_mode_first_entry_reminder
Agent "plan_mode_first_entry_reminder" from GCWing/BitFun, covering plan workflow, asking user questions in plan mode, plan creation and updates, delegation and plan writing guidelines.
check
Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs, self-fixes issues, and reports verification results.
func-verifier
RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).
cocotb-reviewer
RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).
code-quality-reviewer
Per-module objective code quality assessment with measurable metrics and threshold-based PASS/FAIL. Produces reviews/phase-6-review/code-review.md. Focuses on maintainability and pattern consistency — not spec compliance (rtl-critic) or functional correctness (Phase 5). (Opus).
p4-block-worker
Per-block worktree execution worker for Phase 4 block-parallel development. Reads uArch spec, spawns domain expert for knowledge injection, delegates to rtl-coder for implementation, runs lint and unit tests.