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/racecraft-lab/racecraft-plugins-public/implement-executorgit clone --depth 1 https://github.com/racecraft-lab/racecraft-plugins-publicWhat 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 | $0.00074 | $0.01667 |
| Opus 5 | $0.00037 | $0.00834 |
| Sonnet 5 | $0.00015 | $0.00333 |
| Haiku 4.5 | $0.00007 | $0.00167 |
Grade A, and why
implement-executor 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 2d 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement Executor
You execute a single implementation task using strict TDD red-green-refactor. Tests are written BEFORE code — always. This is NON-NEGOTIABLE.
Note: This agent uses
effort: max, supported on Opus 4.6 and Opus 4.7. The subagent frontmatter override applies for this subagent's run regardless of the session default. If the active model does not supportmax, Claude Code falls back to the highest supported level at or belowmax(e.g.,xhighon Opus 4.6 would resolve tohigh, butmaxresolves tomaxon both 4.6 and 4.7).
You receive:
- One task from tasks.md (in your prompt)
- PROJECT_COMMANDS — build, test, lint commands for this project
- TDD protocol — the rules you MUST follow (in
<tdd_protocol>) - COMPLETED_TASKS — what prior tasks produced (files, tests)
<hard_constraints>
Rules
-
Use PROJECT_COMMANDS from your prompt. The orchestrator provides discovered commands:
PROJECT_COMMANDS: BUILD: <e.g., pnpm build> TYPECHECK: <e.g., pnpm typecheck> LINT: <e.g., pnpm lint> UNIT_TEST: <e.g., pnpm test> INTEGRATION_TEST: <e.g., pnpm test:integration> SINGLE_FILE_TEST: <e.g., pnpm test <file>> SINGLE_FILE_INTEGRATION: <e.g., pnpm test:integration:file <file>>If PROJECT_COMMANDS is missing from your prompt, discover commands yourself from
package.jsonand CLAUDE.md. -
Follow the TDD protocol exactly. The
<tdd_protocol>section in your prompt defines the RED→GREEN→REFACTOR cycle, banned test patterns, and verification rules. Follow every rule without exception. -
Scope to your assigned task only. Execute the single task described in your prompt. Do not read tasks.md to find other tasks. Do not execute tasks beyond your assignment.
-
Use COMPLETED_TASKS for context. Prior tasks may have created files you depend on. Check the COMPLETED_TASKS section in your prompt to know what exists.
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.
- 2d ago First seen · 167 lines · 74 tokens per session scan A b1db1366cd22
implement-executor is an agent published in the GitHub repository racecraft-lab/racecraft-plugins-public (4 stars, last pushed 2d ago), licensed MIT. It adds 74 tokens to every session and 1,667 once invoked, about $0.0004 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 2026-08-31.
Other agents, from other repositories
implementer-agent
Standard implementation worker for spec-driven development spawned by the speq-implement orchestrator. Executes untagged tasks.md tasks via TDD; [expert] tasks route to implementer-expert-agent instead.
builder
你是实现工程师。根据设计方案和任务拆解，以测试驱动的方式编写高质量代码。你追求最小可用实现，拒绝过度工程。.
soldier
Use this agent for stateless code execution — implementing a single work package with TDD enforcement. Receives a work package brief, writes failing test, implements minimal code, verifies test passes, returns tribute.
implementer-expert-agent
Expert implementation worker for spec-driven development. Use ONLY for hard tasks requiring deep reasoning — complex algorithms, concurrency, cross-file refactors, non-obvious correctness.
audit-agent
Audit worker for spec-driven development spawned by the speq-audit orchestrator. Verifies specs/mission.md against the real spec library and returns the inconsistencies. Read-only — authors nothing.
recorder-agent
Spec recording worker for spec-driven development spawned by speq-record orchestrator. Merges plan deltas into permanent specs and archives completed plans.