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/wellapp-ai/well/phasingnpx skills add WellApp-ai/Well --skill phasinggit clone --depth 1 https://github.com/WellApp-ai/WellWhat 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 | $0.00013 | $0.01187 |
| Opus 5 | $0.00006 | $0.00593 |
| Sonnet 5 | $0.00003 | $0.00237 |
| Haiku 4.5 | $0.00001 | $0.00119 |
Grade A, and why
phasing 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 3d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phasing Skill
Group implementation slices into phases based on combined risk and GTM scores, then generate a visual timeline.
When to Use
- During Ask mode Phase 2 (CONVERGE), after dependency-mapping and gtm-alignment
- Before transitioning to Plan mode
- To generate the final delivery timeline
Instructions
Phase 1: Gather Scores
Collect scores from previous skills:
| Slice | Risk Score | GTM Score |
|---|---|---|
| [From dependency-mapping] | [N] | [From gtm-alignment] |
Phase 2: Calculate Combined Score
Final Priority Score = Risk - (GTM x 0.5)
Lower score = ships earlier
| Slice | Risk | GTM | Final | Rank |
|---|---|---|---|---|
| #2.2 Invite Flow | 7 | 8 | 3.0 | 1 |
| #1.1 Switcher | 1 | 4 | -1.0 | 2 |
| #1.2 Members UI | 4 | 3 | 2.5 | 3 |
Phase 3: Group into Phases
Apply grouping rules:
| Phase | Criteria | Typical Contents |
|---|---|---|
| Phase 1 | P1 + Lowest risk + Serves T1 | FE-only components, quick wins |
| Phase 2 | P2 + Dependencies on P1 complete | FE+BE integration, non-breaking |
| Phase 3 | P3/P4 + Highest risk | Contract changes, data model |
Grouping Constraints:
- Respect dependency order (check DSM matrix from dependency-mapping)
- Each phase should be independently deployable
- Each phase should serve at least one complete persona tier
- Keep phases to 3-5 days when possible
Phase 4: Generate Timeline (ASCII)
Use ASCII format grouped by stack. Show only dependencies with arrows. No dates or effort estimates.
ASCII Timeline Format:
TIMELINE: [Feature Name]
═══════════════════════════════════════════════════════════
FRONTEND
├── [Slice name]
├── [Slice name] ───────────────┐
├── [Slice name] ───────────────┼──┐
└── [Slice name] ───────────────┘ │
│
BACKEND │
└── [Slice name] ◄─────────────────┘
│
▼
INFRASTRUCTURE
└── [Slice name]
│
▼
INTEGRATION
├── [Slice name]
└── [Slice name]
═══════════════════════════════════════════════════════════
LEGEND:
├── = parallel (no dependency)
──► = dependency (must complete before)
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.
- 3d ago First seen · 154 lines · 13 tokens per session scan A 654ef156c034
phasing is a skill published in the GitHub repository WellApp-ai/Well (340 stars, last pushed 26d ago), licensed MIT. It adds 13 tokens to every session and 1,187 once invoked, about $0.0001 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
auto-reader-ocr
Extract text from images/PDFs (Arabic-first, manga-aware Japanese, 13+ languages auto-detected), translate between 100+ languages, and pull structured fields from invoices/receipts/IDs via the Auto-Reader OCR API. Use when the user shares a document image or PDF to read, translate, or extract data from — or asks for…
server-setup
Initialize tRPC with initTRPC.create(), define routers with t.router(), create procedures with .query()/.mutation()/.subscription(), configure context with createContext(), export AppRouter type, merge routers with t.mergeRouters(), lazy-load routers with lazy().
client-setup
Create a vanilla tRPC client with createTRPCClient (), configure link chain with httpBatchLink/httpLink, dynamic headers for auth, transformer on links (not client constructor). Infer types with inferRouterInputs and inferRouterOutputs. AbortController signal support. TRPCClientError typing.
non-json-content-types
Handle FormData, file uploads, Blob, Uint8Array, and ReadableStream inputs in tRPC mutations. Use octetInputParser from @trpc/server/http for binary data. Route non-JSON requests with splitLink and isNonJsonSerializable() from @trpc/client. FormData and binary inputs only work with mutations (POST).
caching
Set HTTP cache headers on tRPC query responses via responseMeta callback for CDN and browser caching. Configure Cache-Control, s-maxage, stale-while-revalidate. Handle caching with batching and authenticated requests. Avoid caching mutations, errors, and authenticated responses.
portaljs-connect-ckan
Wire a scaffolded PortalJS portal to a CKAN backend over its API. Generates a tiny server-side fetch client (no runtime dependency) and feeds the /search catalog and /@namespace/slug showcases from CKAN instead of datasets.json. Use when connecting an existing portal to a live CKAN instance instead of a static…