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 skills add vmobifystudio/app-dev-team --skill process-tieringgit clone --depth 1 https://github.com/vmobifystudio/app-dev-teamWrote 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/vmobifystudio/app-dev-team/process-tiering)<a href="https://agentmods.dev/skills/vmobifystudio/app-dev-team/process-tiering"><img src="https://agentmods.dev/badge/skills/vmobifystudio/app-dev-team/process-tiering/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/vmobifystudio/app-dev-team/process-tiering"><img src="https://agentmods.dev/badge/skills/vmobifystudio/app-dev-team/process-tiering.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00087 | $0.01042 |
| Opus 5.5 | $0.00035 | $0.00417 |
| Sonnet 5.5 | $0.00017 | $0.00208 |
| Haiku 4.5 | $0.00009 | $0.00104 |
Grade A, and why
process-tiering 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 1mo 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Process tiering
Mined from studying rsmdt/the-startup (tiered Direct/Standard/Factory dispatch) and
olehsvyrydov/AI-development-team (change_classes → track mapping) — both scale process weight
to task size instead of running the same ceremony on everything. This studio already has the input
those systems built new fields for: cpo's backlog already estimates every item XS/S/M/L/XL
(agents/cpo.md), and board.mjs add --estimate already carries it onto the ticket. This skill is
the mapping from that existing field to how much process the ticket actually needs — no new field,
no new ticket state.
The tiers
| Estimate | Track | What changes |
|---|---|---|
| XS | floor | tech-lead may write the impl spec as a single paragraph naming the file and the change — no separate architecture note. code-reviewer still runs the full review, but §4b's on-device-measurement and round-trip-execution requirement applies only if the change touches a value a user supplies, sees, or is told (§4b's own trigger condition, unchanged) — most XS tickets don't. |
| S | light | Impl spec covers acceptance criteria and the file(s) touched, no separate design-pattern section. Full review, full §4b when it applies. |
| M | standard | Today's default — full impl spec, full review. No change from current behavior. |
| L / XL | full | Impl spec must name reusable patterns for the pod (tech-lead's existing job, made explicit as required rather than optional at this size) and cross-reference the architecture doc section it extends. Review adds defect-hunting §1 (second write path) as a named, mandatory step in the verdict, not just available — the larger the change, the more likely it has a second write path nobody enumerated. |
What never tiers down — the safety override
A ticket is full tier regardless of its estimate if it touches: authentication, payment/IAP,
PII or any data a privacy-reviewer finding would apply to, or anything security-reviewer owns.
An XS-estimated one-line auth change is still a full-ceremony review. This is not a size question —
an estimate measures how much code moves, not how much damage a wrong line does, and those are
different axes. If a ticket's tier and its estimate disagree, the tier wins and the estimate is
simply wrong-sized, not a reason to skip anything.
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.
- 1mo ago First seen · 59 lines · 87 tokens per session scan A 57294bb0fa9c
process-tiering is a skill published in the GitHub repository vmobifystudio/app-dev-team (4 stars, last pushed 4d ago), licensed MIT. It adds 87 tokens to every session and 1,042 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
tower
The front door: a standing conversational session that takes any ask about the repository in plain language, answers questions, and routes work that changes the repository per request onto visual flight (an isolated worker that lands a draft PR) or instrument flight (the spec pipeline), stating its grounds, with…
paperclip
Use for Paperclip-managed tasks and heartbeats: reading task context, delivering task documents or files, updating completion or blockers, coordinating or delegating work, and following company governance. Includes control plane API operations for assignments, comments, approvals, and routines.
paperclip-board
Manage a Paperclip company as a board member via chat. Use when the user wants onboarding, company or agent management, approvals, task monitoring, cost oversight, or work product review in the Paperclip control plane.
paperclip-distill
Use when an operation issue is a Paperclip cursor-window, distill, or backfill. Turn source-bundled Paperclip activity into wiki-insightful project standups, durable project pages, decisions, and history without asset dereferencing.
summarize-status
Write a short, colloquial summary for a Paperclip summary slot: open with the 1–3 specific, concrete actions the reader needs to take right now to unblock the work, then a brief plain-language status, streaming progress as it works.
paperclip-task-bridge
Create, comment on, update, and list Paperclip tasks from Hermes using scoped Paperclip API credentials.