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/project-referencenpx skills add phase-rs/phase --skill project-referencegit 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 | $0.00110 | $0.05769 |
| Opus 5 | $0.00055 | $0.02884 |
| Sonnet 5 | $0.00022 | $0.01154 |
| Haiku 4.5 | $0.00011 | $0.00577 |
Grade A, and why
project-reference 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 — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.
phase.rs Project Reference
Lookup material for build commands, the verification cadence, architecture, environment variables, releasing, and CI. The always-on rules (design principles, Tilt-not-cargo, building blocks, CR annotations, Rust idioms) live in the root CLAUDE.md / AGENTS.md; this skill holds the on-demand reference that doesn't need to be resident every turn.
Tilt resources & operational rules
Tilt is always running and continuously rebuilds on file changes. Do NOT run cargo build, cargo clippy, cargo test -p phase-engine, pnpm run type-check, or pnpm lint directly — they compete for cargo target locks. Check Tilt logs instead.
Available Tilt resources (defined in Tiltfile):
| Resource | What it does | Triggers on |
|---|---|---|
clippy |
cargo clippy --all-targets -- -D warnings |
crates/ changes |
test-engine |
cargo test -p phase-engine |
crates/engine/src/ changes |
test-ai |
cargo test -p phase-ai |
crates/engine/src/ or crates/phase-ai/src/ changes |
wasm |
WASM build (depends on clippy) | engine/AI/WASM src changes |
card-data |
./scripts/gen-card-data.sh |
crates/engine/src/ changes |
check-frontend |
pnpm run type-check && pnpm lint |
client/src/ changes |
test-frontend |
pnpm test -- --run |
client/src/ changes |
server |
Build + serve phase-server | server src changes |
coverage |
cargo coverage |
Manual trigger only |
How to check results:
tilt logs clippy --tail 30 --since 2m # Recent clippy output
tilt logs test-engine --tail 50 --since 2m # Recent test results
tilt logs card-data --tail 20 --since 1m # Card data gen output
tilt logs check-frontend --tail 30 --since 2m # TS type-check + lint
How to wait for current results without dumping logs:
./scripts/tilt-wait.sh clippy test-engine card-data # wait until all settle (no timeout)
./scripts/tilt-wait.sh --interval 10 clippy # poll faster for a single fast resource
./scripts/tilt-wait.sh --timeout 600 clippy test-engine # bound the wait
Exit codes: 0 all ok, 1 a resource is in terminal error (updateStatus=error with no in-flight build), 2 usage error, 3 cannot answer the question, 124 timeout (only when --timeout is set). The script prints one <resource> status=… current=… last=… line per tick so you can see why a wait is taking time without paying for log payloads. After exit 1, fetch details with tilt logs <resource> --tail 50 --since 2m.
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 · 306 lines · 110 tokens per session scan A 76d73fbb793f
project-reference is a skill published in the GitHub repository phase-rs/phase (259 stars, last pushed 2d ago), licensed Apache-2.0. It adds 110 tokens to every session and 5,769 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 2026-08-30.
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.