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/add-engine-variant/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/add-engine-variant)<a href="https://agentmods.dev/skills/phase-rs/phase/add-engine-variant"><img src="https://agentmods.dev/badge/skills/phase-rs/phase/add-engine-variant/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/add-engine-variant"><img src="https://agentmods.dev/badge/skills/phase-rs/phase/add-engine-variant.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
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 →
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
- medium Excessive Agency · line 133 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00096 | $0.03657 |
| Opus 5.5 | $0.00038 | $0.01463 |
| Sonnet 5.5 | $0.00019 | $0.00731 |
| Haiku 4.5 | $0.00010 | $0.00366 |
Grade A, and why
add-engine-variant 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 2mo 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
add-engine-variant — Engine Enum Extension Gate
When to invoke
This skill is the gate for any work that would add a variant to an existing engine enum. Run it BEFORE:
- Proposing an engine extension in a plan or task description
- Drafting an engine PR that adds a variant
- Approving an audit verdict of "engine extension required"
- Wiring a converter arm to a not-yet-existing variant
If you find yourself about to type pub enum Foo { ... NewVariant ... } in crates/engine/src/, pause and run this skill.
The three filter stages — all must pass
Stage 1: Existence verification (5-grep protocol)
The variant might already exist under a different engine-native name. External data formats and the engine vocabulary are not 1:1; the engine often has the concept under a different name.
The canonical engine surface is
data/engine-inventory.json(gitignored). Runcargo engine-inventoryto (re)generate it locally before grepping for existing variants.
Run all five searches before considering extension:
# 1. Direct name search
rg -n "<concept_keyword>" crates/engine/src/types/
# 2. Inverse concept (engine often expresses "not X" as "X { negated: bool }" or "X { negated: true }")
rg -n "<inverse_concept>" crates/engine/src/types/
# 3. Inversion-parameter variants
rg -n "negated: bool|invert|polar" crates/engine/src/types/ability.rs
# 4. Native parser reverse dictionary — how does oracle_nom express this concept?
rg -n "<concept_keyword>|<engine_concept>" crates/engine/src/parser/oracle_*.rs
# 5. Synthesis layer
rg -n "<concept_keyword>" crates/engine/src/database/synthesis.rs
Stage 1 verdicts:
- EXISTS_SAME_NAME: variant exists. Stop. Wire to it.
- EXISTS_DIFFERENT_NAME: concept exists under an engine-native name (e.g., an external
CreateTriggerUntilmaps to engineEffect::CreateDelayedTrigger). Stop. Map the source data to the existing slot. - EXISTS_AS_PARAMETER: concept exists as a parameter value of a more general variant (e.g., "untapped" exists as
Tap { negated: true }). Stop. Use the parameter form. - DOES_NOT_EXIST: proceed to Stage 2.
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.
- 2mo ago First seen · 166 lines · 96 tokens per session scan A d900008c9b51
add-engine-variant is a skill published in the GitHub repository phase-rs/phase (312 stars, last pushed today), licensed Apache-2.0. It adds 96 tokens to every session and 3,657 once invoked, about $0.0004 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
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.
graphify-windows
Turn any folder of files into a navigable knowledge graph with community detection, an honest audit trail, and three outputs: interactive HTML, GraphRAG-ready JSON, and a plain-language GRAPHREPORT.md.
lessons
How to propose and query distilled lessons (the experiential memory). Only project-steward persists; every other agent proposes/queries. Use when you discover a durable lesson or need prior experience for the current task.
webgl-standards
DORMANT (ADR-0017, 2026-07-20) - the TERMINAL VELOCITY scroll-film was retired and apps/landing is a static site with no GL surface; this skill is preserved for any future WebGL rebuild (conventions, verified version pins, playhead/scroll-rig/VAT/Gerstner/post-chain patterns, budgets, gate + semantic-layer machinery).…
agent-cli-standards
Agent-facing CLI standards — the argv-sentinel binary mode, the thin-client-over-the-bridge rule, allowlist projections, prompt-fencing third-party text, the stable machine-readable output contract, exit codes, throttling, and destructive-command operability. Load for changes under extensionbridge/agentcli.rs…
webgl-gate-audit
Procedures for auditing apps/landing TERMINAL VELOCITY WebGL phase gates - driving the browser to exact playhead positions across the 9 scenes, screenshot discipline, scrub + VAT determinism (scrub down THEN rewind to the same playhead -> identical frame), FPS sampling at the risk scenes, draw-call + bundle-size…