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 skills/phase-rs/phase/unlock-setnpx skills add phase-rs/phase --skill unlock-setgit clone --depth 1 https://github.com/phase-rs/phaseWhat 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 | $0.00103 | $0.06330 |
| Opus 5 | $0.00051 | $0.03165 |
| Sonnet 5 | $0.00021 | $0.01266 |
| Haiku 4.5 | $0.00010 | $0.00633 |
Grade A, and why
unlock-set 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 — 440 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unlock Set Cards — Tier-Based Coverage Pass
Derive a set's unsupported card list, cluster by shared missing primitive (not by card), rank clusters by unlock-count × engineering cost, then run each cluster through $engine-implementer sequentially. Commit between clusters. Defer anything that would ship a partial runtime worse than Unimplemented.
When to use this skill vs. parser-velocity
This skill runs the heavy loop: cluster→plan→implement→review per cluster, full gate between clusters, CR annotations, typed primitive work. Right when the work is cluster-level infrastructure (new typed enum variants, new runtime mechanics, new combat/stack/resolver behavior, anything needing CR validation).
Use the companion parser-velocity skill instead when:
- The target cards are "almost supported" — parser recognizes most of the text but misses one variation.
- The fix per card is "add a
tag()arm to an existingalt()" with no runtime work. - You want to iterate across Category A (VerbVariation), B (SubjectStripping), D (StaticCondition), or parser-miss C (TriggerEffect) cards — these are the parser-only categories in
gap_analysis.rs. - You want to defer the full gate (
fmt/clippy/test-all/coverage/semantic-audit) to session end instead of paying it per cluster.
parser-velocity batches edits per compile cycle and avoids the $engine-implementer plan/review overhead — use it for quick wins, then return here for the cluster-level work that remains.
Prereqs. Run from the repo root. The $engine-implementer skill must be available. cargo, jq, ./scripts/gen-card-data.sh, and docs/MagicCompRules.txt must be present (run ./scripts/fetch-comp-rules.sh if missing).
Phase 0 — Resolve the Set
If the user named a set, resolve it to a set code. Otherwise, pick the highest-ROI recent set using the triage rubric below.
# By name (fuzzy):
jq -r 'to_entries[] | select(.value.name | test("<user phrase>"; "i")) | "\(.key)\t\(.value.name)\t\(.value.baseSetSize // 0)\t\(.value.type // "")" ' client/public/set-list.json
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 · 440 lines · 103 tokens per session scan A 88a33ad9157d
unlock-set is a skill published in the GitHub repository phase-rs/phase (259 stars, last pushed 2d ago), licensed Apache-2.0. It adds 103 tokens to every session and 6,330 once invoked, about $0.0005 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 skills, from other repositories
add-card
Implements new Magic: The Gathering cards for the Argentum Engine. Use when adding a new card, the user provides one or more card names to implement, or asks to implement a specific MTG card. Several cards that reuse existing primitives can be implemented together into one PR.
add-feature
Adds a new feature or mechanic to the Argentum Engine (SDK primitive, effect, trigger, condition, static/replacement ability, server/client capability) following the project's architecture and SDK-elegance principles. Use when implementing engine/SDK/server/client functionality that isn't a single card — e.g. "add an…
verify-set
Prove a Magic set is actually finished — card-for-card complete, field-for-field faithful to Scryfall, scripts that match their oracle text, tokens that resolve the set's own art, behaviourally sound — then archive its backlog. Builds the Scryfall dump and CardFieldVerificationTest, fans the per-card DSL and token…
assay-ready-sweep
Implement every "Assay-ready" card for a Magic set — the cards Argentum Assay reads whole that the set hasn't authored yet — placing each canonical in its earliest real printing and giving the sweep's own set a Printing row when the card is a reprint. Computes the four-way split first, authors to assay compile's JSON…
create-backlog-for-set
Create the backlog/sets/ / entry for a Magic set — download the whole set from Scryfall (cached alongside Assay's cache), write cards.md as a per-colour checklist with the already-implemented cards ticked, scaffold the set's definitions/ / module if it doesn't exist, and write mechanics.md ordering every mechanic the…
add-random-card
Pick a random unimplemented card from a set and implement it. Accepts either a backlog cards.md path or a set name/code.