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/bug-coverage-classifiernpx skills add phase-rs/phase --skill bug-coverage-classifiergit 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 | $0.00100 | $0.01837 |
| Opus 5 | $0.00050 | $0.00919 |
| Sonnet 5 | $0.00020 | $0.00367 |
| Haiku 4.5 | $0.00010 | $0.00184 |
Grade A, and why
bug-coverage-classifier scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "https://data.phase-rs.dev/preview/coverage-data.json" \ How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bug Coverage Classifier
What this skill is for
The actionable signal is supported_aspect_defect — a card claims to support the clause the user is reporting on, but the engine is still misbehaving. That is the bug worth filing.
Everything else is either already-known or out-of-scope:
unsupported_aspect— explicitly markedsupported: falseinparse_details. We already know it doesn't work. Defer unless the fix is trivial. No investigation needed beyond confirming the verdict.not_card_data_attributable— the bug is not about card text at all (combat assignment, AI behavior, UI, multiplayer, deckbuilder). Route to the relevant subsystem; the parser/effect-handler can't be the cause.cannot_determine— the report doesn't pin to any clause. Ask for clarification.
Spend your effort on supported_aspect_defect. That is where bugs actually live.
Inputs
card_name— the card the bug report names (e.g."Archon of Cruelty").bug_description— what the user said is misbehaving.
What to do
1. Look up the card
curl -s "https://data.phase-rs.dev/preview/coverage-data.json" \
| jq --arg n "<card_name>" '.cards[] | select(.card_name == $n) | {oracle_text, supported, parse_details}'
For repeat lookups in the same session, cache the full coverage JSON to a tmp file once and jq against the file.
If jq returns nothing, try common name normalizations: drop apostrophes (Bloodchief's Ascension → Bloodchief Ascension), try the front face of an MDFC, fix obvious typos. Consult triage/unknown-card-mapping.json for known corrections. If the name is flagged not_a_card (e.g. token types like "Blood Token"), return verdict not_card_data_attributable.
2. Identify which clause the bug is about
Read the bug description and match it to the parse_details node whose source_text describes the misbehaving line. The card name is already pinned, so you're choosing among at most a handful of clauses. Use natural-language judgement — bug reports use synonyms, abbreviations, and game-state examples ("X=3", "on end step", "with 2 counters") that won't always share vocabulary with the Oracle text.
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 · 119 lines · 100 tokens per session scan A 7ad1dbe09f8f
bug-coverage-classifier is a skill published in the GitHub repository phase-rs/phase (259 stars, last pushed 2d ago), licensed Apache-2.0. It adds 100 tokens to every session and 1,837 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
qa-cli-mcp-api
Select and run explicitly requested, risk-based QA for Anarlog's CLI, webhooks, stdio MCP, hosted Cloud API, and remote MCP. Test only affected lanes unless comprehensive coverage is requested.
product-update-newsletter
Draft, update, or audit a crisp, changelog-grounded Anarlog product-update newsletter in Loops (app.loops.so) for a desktop release. Use after the changelog is merged, when asked to draft, revise, or pre-send check the release announcement email.
sqlite-schema-design
Design or review schemas for crates/cloudsync using SQLite Sync constraints, not generic SQLite advice. Use when adding synced tables, changing synced columns, or planning CloudSync-safe migrations.
release-new-version
Release a new desktop stable version for Anarlog. Use when asked to cut, publish, or prepare a new stable desktop release after checking and merging the changelog.
fix-ready-prs
Inspect every open non-draft PR for CI failures and unresolved Cursor Bugbot findings, then fix them on the existing PR branches. Use when asked to check active PRs, triage ready PRs, fix CI, or address Bugbot comments.
reactive-sqlite-ui
Build SQLite-backed reactive UI in apps/desktop using stable patterns for reads, selection, forms, writes, and loading states. Use when implementing or reviewing screens built on useDrizzleLiveQuery and SQLite mutations.