Borrowing it
Nothing to install: this file belongs to phase-rs/phase. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/phase-rs/phase/main/.claude/skills/engine-implementer/SKILL.mdgit clone --depth 1 https://github.com/phase-rs/phaseWrote 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/skills/phase-rs/phase/engine-implementer)<a href="https://agentmods.dev/skills/phase-rs/phase/engine-implementer"><img src="https://agentmods.dev/badge/skills/phase-rs/phase/engine-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/skills/phase-rs/phase/engine-implementer"><img src="https://agentmods.dev/badge/skills/phase-rs/phase/engine-implementer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 142 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00055 | $0.10312 |
| Opus 5.5 | $0.00022 | $0.04125 |
| Sonnet 5.5 | $0.00011 | $0.02062 |
| Haiku 4.5 | $0.00006 | $0.01031 |
Grade A, and why
engine-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 10d 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 — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engine Implementer (Orchestrator)
This is the orchestrator for the phase.rs implementation pipeline. It runs as a skill in the main thread so it can spawn a fresh agent for every step that benefits from fresh context (planning, plan review, implementation, implementation review). Do not turn this into an agent — agents cannot spawn sub-agents, which is what made earlier versions silently degrade.
Roles
| Step | Where it runs | Why |
|---|---|---|
| 1. Produce plan | Fresh agent invoking engine-planner |
The plan is shaped by the task, not by the conversation history that led here |
| 2. Review plan | Fresh agent invoking review-engine-plan |
Honest architectural review, independent of the planner |
| 3. Implement | Fresh agent following executor.md | Surgical edits and preparatory checks; never commits |
| 4. Checkpoint; schedule measurement | This thread; a fresh measurement executor when due | Commit now; batch parser measurement at the final combined candidate unless needed to proceed |
| 5. Complete verification | This thread | Verify the committed candidate, never an in-flight working tree |
| 6. Review implementation | Fresh agent invoking review-engine-impl |
Independent review of the immutable base-to-candidate diff |
| 7. Final acceptance | This thread | Accept only the exact reviewed checkpoint candidate or its Step 6 comment-only correction commit |
Spawning by runtime. Skills are invoked as /name under Claude Code and $name under Codex; both read .claude/skills/<name>/SKILL.md (.agents/skills and .codex/skills link there). Under Claude Code, spawn general-purpose agents for Steps 1, 2 and 6 and the engine-implementation-executor agent type for Steps 3 and 4, which loads executor.md. Under Codex, spawn a worker agent per step and tell it which skill or file to read first — for Steps 3 and 4, .claude/skills/engine-implementer/executor.md. A runtime that cannot spawn agents runs each step in a fresh session and hands every reviewer ONLY the artifact under review (the full plan, or the unified diff), the original task, CLAUDE.md, the relevant review skill, the attempt history below, and in chartered runs the charter, phase index and deferral allowlist — never the conversation that produced the artifact. Never degrade to reviewing your own work in the same context; that is the failure this skill exists to prevent. If even a fresh session is impossible, say so in the final report and in the PR body under "Validation Failures"; do not claim the review loop ran clean.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago Changed b989dc8bbb3a
- 11d ago Changed · +15 lines 8b96f8bcf2b0
- 14d ago Changed · +5 lines bf716ae912e1
- 15d ago Changed 9e2cbc36c0fb
- 21d ago Changed · +18 lines 3204713691b0
- 22d ago Changed · +8 lines 511e59ac27ca
- 25d ago Changed · +28 lines eb56335d4199
- 1mo ago Changed · +14 lines f5b819424e80
- 1mo ago Changed · -66 lines · +12 tokens per session bb06986f2ab7
- 1mo ago First seen · 264 lines · 43 tokens per session scan A 5d172350e9eb
engine-implementer is a skill published in the GitHub repository phase-rs/phase (313 stars, last pushed today), licensed Apache-2.0. It adds 55 tokens to every session and 10,312 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 2026-08-30.
Other skills, from other repositories
compiler-commit
Use when you want to verify compiler changes and commit with the correct convention. Runs tests, lint, and format, then commits with the [compiler] or [rust-compiler] prefix.
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
gh-find-prs
Survey open Codewhale PRs and triage each for mergeability and disposition against the real landing branch.
github
Skill "github" from Hmbown/Codewhale, covering github, when to use, setup, workflow and non-goals.
anarlog
Query Anarlog meetings, notes, summaries, transcripts, participants, action items, and recurring history, or import a local recording. Use when a user asks about their Anarlog meeting data or needs meeting context for another task.
cosmos-pre-commit-validation
Run pre-commit checks for a specific set of crates. Use this when validating changes under sdk/cosmos before committing or during code review.