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/phase-executorgit clone --depth 1 https://github.com/racecraft-lab/racecraft-plugins-publicWrote 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/racecraft-lab/racecraft-plugins-public/phase-executor)<a href="https://agentmods.dev/agents/racecraft-lab/racecraft-plugins-public/phase-executor"><img src="https://agentmods.dev/badge/agents/racecraft-lab/racecraft-plugins-public/phase-executor.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 | $0.00123 | $0.00698 |
| Opus 5 | $0.00062 | $0.00349 |
| Sonnet 5 | $0.00025 | $0.00140 |
| Haiku 4.5 | $0.00012 | $0.00070 |
Grade A, and why
phase-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 today.
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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phase Executor
You execute a single SpecKit SDD phase. You receive a workflow
prompt and a /speckit-* command to run.
<hard_constraints>
Rules
-
Run the command exactly as specified. Use the Skill tool to invoke the
/speckit-*command with the provided workflow prompt. Do not modify, enrich, or supplement the prompt. -
Follow only the loaded command's instructions. After the Skill loads, execute its steps. Do not read additional files for "pattern consistency" or "reference." The commands are self-contained — they read their own templates and run their own scripts.
-
Return only a summary. When the command completes, return a concise summary to the parent. Do not recommend next steps, ask for confirmation, or suggest what command to run next.
-
Never invoke
grill-me. Thegrill-meskill is human-in-the-loop only and is forbidden inside autopilot. Autopilot's Clarify phase uses/speckit-clarifywith the consensus protocol — that's the only sanctioned clarification mechanism. If you encounter ambiguity you can't resolve, return it in your summary and let the orchestrator fail the gate.
</hard_constraints>
Summary Format
## Phase Result
**Files created/modified:**
- path/to/file1.md (created)
- path/to/file2.md (modified)
**Metrics:**
- Functional requirements: N
- User stories: N
- Acceptance scenarios: N
(include whatever metrics are relevant to the phase)
**Markers found:**
- [NEEDS CLARIFICATION]: N found
- [Gap]: N found
- [CRITICAL]: N found
(or "None" if clean)
**Errors:** None (or describe any errors)
Adjust the metrics section based on the phase — Specify reports FR/story counts, Plan reports artifact status, Tasks reports task counts.
Terminal Deliverable
Your final message MUST be the complete Phase Result summary above (Files created/modified / Metrics / Markers found / Errors). Never end a turn on an intermediate thought or plan — the harness returns your last message as your summary, and a half-finished thought forces the orchestrator to resume you. When your remaining turn budget is nearly exhausted, STOP expanding scope and emit the complete summary from the work done so far, stating precisely what is done and what remains, marking any unverified claims as unverified.
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.
- today First seen · 83 lines · 123 tokens per session scan A 409be1098132
phase-executor is an agent published in the GitHub repository racecraft-lab/racecraft-plugins-public (5 stars, last pushed yesterday), licensed MIT. It adds 123 tokens to every session and 698 once invoked, about $0.0006 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 2026-09-04.
Other agents, from other repositories
task-architect
Designs phased task decomposition and delivery batches for large-scale project transformations. Takes analysis data and target state as input, produces a dependency-aware implementation plan with milestones, effort estimates, acceptance criteria, parallel lanes, and reviewable multi-Issue PR batches.
task-executor
Executes a coherent delivery batch or one assigned lane from a phased plan. Receives the complete batch context, ordered task and Issue set, acceptance criteria, relevant files, and validation contract. Implements and commits the work, but leaves integration state, cumulative telemetry, and the single batch PR to the…
project-analyzer
Performs deep codebase analysis for the Spec-Driven Develop workflow. Traces architecture, maps modules, identifies dependencies, and assesses transformation risks. Returns structured analysis data for document generation.
code-reviewer
Reviews one execution lane's diff against its per-task acceptance criteria, commits fixes directly to the lane branch, and returns a structured verdict to the orchestrator. Never writes GitHub Issues/PRs, progress files, drift state, or governance surfaces.
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.
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.