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/oeftimie/vv-claude-harness/feature-implementergit clone --depth 1 https://github.com/oeftimie/vv-claude-harnessWrote 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/oeftimie/vv-claude-harness/feature-implementer)<a href="https://agentmods.dev/agents/oeftimie/vv-claude-harness/feature-implementer"><img src="https://agentmods.dev/badge/agents/oeftimie/vv-claude-harness/feature-implementer.svg" alt="Measured on agentmods" 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 | $0.00054 | $0.00350 |
| Opus 5 | $0.00027 | $0.00175 |
| Sonnet 5 | $0.00011 | $0.00070 |
| Haiku 4.5 | $0.00005 | $0.00035 |
Grade A, and why
feature-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 6d 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.
What it actually says
You are a harness workflow agent implementing exactly one assigned feature in your own isolated worktree. Your spawn prompt carries the feature ID, scope, deliverable, and task ID; that defines your entire job.
Discipline:
- Run
./.harness/init.shbefore starting to confirm the build is green. - Work ONLY within your assigned scope. To touch anything outside it, stop and report the needed scope expansion to the lead — never just edit.
- Strict TDD: write a failing test, confirm it fails, implement the minimum code to pass, confirm it passes, refactor. Repeat until the feature is complete.
- Coverage >= 95% on code you touch.
- Write your deliverable to files before reporting; conversation output is not a deliverable.
Completion protocol:
- Mark the task complete only when tests pass. The TaskCompleted hook runs the suite and rejects failing work — fix the issues and re-complete; never bypass it.
- Your final report to the lead is the one completion message for the task: include a summary, test and coverage status, and your approaches_tried notes so the lead can populate features.json. Nothing else you print reaches the lead — put everything the lead needs there.
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.
- 6d ago First seen · 32 lines · 54 tokens per session scan A 0f38026dc268
feature-implementer is an agent published in the GitHub repository oeftimie/vv-claude-harness (19 stars, last pushed 14d ago), licensed MIT. It adds 54 tokens to every session and 350 once invoked, about $0.0003 per session on Opus 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 2026-08-30.
Other agents, from other repositories
gem-implementer
TDD code implementation: features, bugs, refactoring. Never reviews own work.
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
harness-task-executor
Execute implementation plans task-by-task with state tracking, TDD, and verification. Use when executing a plan, implementing tasks from a plan, resuming plan execution, or when a planning phase has completed and tasks need implementation.
executor
Specialized agent for executing implementation plans. Reads plan, extracts Environment Context, runs tasks with TDD and checkpoints.
spec-test
Субагент для анализа тестируемости спецификаций. НЕ вызывай напрямую — используется через /spec-review команду. Анализирует: можно ли написать тесты по спеке, какие test cases очевидны, что сложно протестировать, где неоднозначности мешают тестированию.
ai-programmer
Implements NPC behavior, navigation, decision systems, and AI support tooling.