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/session-statusnpx skills add WellApp-ai/Well --skill session-statusgit clone --depth 1 https://github.com/WellApp-ai/WellWrote 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/wellapp-ai/well/session-status)<a href="https://agentmods.dev/skills/wellapp-ai/well/session-status"><img src="https://agentmods.dev/badge/skills/wellapp-ai/well/session-status.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00016 | $0.01230 |
| Opus 5 | $0.00008 | $0.00615 |
| Sonnet 5 | $0.00003 | $0.00246 |
| Haiku 4.5 | $0.00002 | $0.00123 |
Grade A, and why
session-status 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 5d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Status Skill
Generate consistent navigation breadcrumbs showing current position, takt time, and session metrics.
When to Use
- At START of every Ask/Agent/Plan mode response
- At END of every Ask/Agent/Plan mode response
- When session metrics are needed for Session Journal sync
Phase 1: Gather State
Collect current session state:
| Data | Source |
|---|---|
| Feature name | From init context or branch name |
| Current phase | DIVERGE / CONVERGE / DEFINE / AGENT |
| Loop count | Incremented on each user feedback cycle |
| Progress | Validated items / total items |
| Duration | Time since phase started |
| Status | G (flow) / Y (waiting) / R (stopped) |
Phase 2: Calculate Takt
Compare duration against targets from 03-shared.mdc:
| Phase | Target | Warning | Stop |
|---|---|---|---|
| DIVERGE (per loop) | 15min | 30min | 60min |
| CONVERGE | 20min | 40min | 90min |
| DEFINE | 10min | 20min | 45min |
| Commit (each) | 10min | 20min | 30min |
Determine suffix:
- Under target: (none)
- Warning exceeded:
! - Stop exceeded:
!!
Phase 3: Format Header
Generate single-line breadcrumb:
Format: [STATUS] | [Feature] | [PHASE_PROGRESS] | L[N] | [X]/[Y] | [TIME]
Examples by phase:
- DIVERGE:
G | Collaboration | DIVERGE ###....... | L3 | 5/9 | 18m - CONVERGE:
G | Collaboration | DIVERGE OK | CONVERGE ##.... | L1 | 22m - DEFINE:
G | Collaboration | DIVERGE OK | CONVERGE OK | DEFINE ###.. | L2 | 35m - AGENT:
G | Collaboration | AGENT | C2/5 | 45m - Warning:
Y | Collaboration | DIVERGE ###....... | L3 | 5/9 | 32m! - Stopped:
R | Collaboration | AGENT | JIDOKA STOP
Progress bar: 10 chars, # filled, . empty, proportional to completion.
Phase 4: Format Footer
Generate context-specific footer:
---
Next: [action prompt]
Dynamic prompts by context:
| Context | Footer Prompt |
|---|---|
| DIVERGE with DIG | Provide OK/KO/DIG for: #4, #6, #7 |
| Gate 1 passed | All validated. Say "converge" to proceed. |
| Gate 2 | Choose option: A / B / C |
| Gate 3 | Approve phasing: OK / REORDER / SPLIT |
| AGENT | Commit 2/5 in progress... |
| Jidoka stop | Reply with A, B, C, or D |
| Autonomous | Iteration 3/5... |
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.
- 5d ago First seen · 181 lines · 16 tokens per session scan A 53988e1b8342
session-status is a skill published in the GitHub repository WellApp-ai/Well (339 stars, last pushed 28d ago), licensed MIT. It adds 16 tokens to every session and 1,230 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…
nextjs-pages-router
Set up tRPC in Next.js Pages Router with createNextApiHandler, createTRPCNext, withTRPC HOC, SSR via ssr option and ssrPrepass, SSG via createServerSideHelpers with getStaticProps, and server-side helpers for getServerSideProps prefetching.
react-query-setup
Set up @trpc/tanstack-react-query with createTRPCContext(), TRPCProvider, useTRPC() hook, queryOptions/mutationOptions factories, query invalidation via queryClient.invalidateQueries with queryFilter, and type inference with inferInput/inferOutput.
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).
scalar-docs
Skill for writing and updating scalar.config.json — Scalar Docs configuration reference for users and LLMs.
horse-integration-tests
Guide for writing automated integration tests for Horse endpoints using DUnit/DUnitX and THTTPClient.