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/vmobifystudio/app-dev-team/role-activationnpx skills add vmobifystudio/app-dev-team --skill role-activationgit 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/role-activation)<a href="https://agentmods.dev/skills/vmobifystudio/app-dev-team/role-activation"><img src="https://agentmods.dev/badge/skills/vmobifystudio/app-dev-team/role-activation.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 | $0.00082 | $0.05852 |
| Opus 5 | $0.00041 | $0.02926 |
| Sonnet 5 | $0.00016 | $0.01170 |
| Haiku 4.5 | $0.00008 | $0.00585 |
Grade A, and why
role-activation 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 today.
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 — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role activation
The roster is not fixed. A three-screen utility does not need a CEO and a CPO, and a backend
service does not need an ASO specialist, a store-readiness gate, or a runtime gate hunting for an
.xcodeproj. Activation has two axes, and both are decided once, up front, and written down.
- Tier —
flagship|utility. How much process the work deserves (House KB §Tiers). - Product type —
ios-app|android-app|mobile-app|backend-service|web-app|cli|library. Which specialists exist at all.
A deactivated role is recorded, never silently absent. Everything below exists to serve that one rule: an absent role and a skipped role must stay distinguishable six months later.
Determining the two axes
Greenfield — from docs/01-intake.md, which requirements-intake has already written:
- Product type ← its
## Product typeanswer (intake question 3). One answer, verbatim. - Tier ← an explicit
--utility/--flagshipflag if the user passed one; otherwise derive: utility when the intake describes a single-purpose tool with one core action and no subscription, content library, or AI system; flagship otherwise. State the derived tier and its evidence in the Gate 1 brief — it is a scope decision, and Gate 1 is where scope is approved.
Brownfield — from brownfield-onboarding Step 1 detection, never from a README:
| Detected | Product type |
|---|---|
*.xcodeproj / *.xcworkspace only |
ios-app |
settings.gradle* + app/ only |
android-app |
| both of the above | mobile-app |
package.json with a web framework, or any public/+index.html |
web-app |
server framework or Dockerfile/Procfile, no UI surface |
backend-service |
a binary entry point (bin, cmd/, main.go, [[bin]]) and no UI |
cli |
| a package manifest that publishes, with no entry point | library |
Tier for brownfield: derive from the app's size and shape (module count, subscription/ads SDKs present), and say which signal decided it. When detection is ambiguous, ask the user one question — do not guess. A wrong product type turns off the wrong specialists.
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.
- today First seen · 286 lines · 82 tokens per session scan A fbd29fc2af3f
role-activation is a skill published in the GitHub repository vmobifystudio/app-dev-team (4 stars, last pushed 25d ago), licensed MIT. It adds 82 tokens to every session and 5,852 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
execute-task
Implement one task (or a cohesion bundle) from a signed-off spec (Ready or Active): recompute the execution freshness gate, write the verifying test first, implement to green, run the project's full CI with adaptive retry, converge via the configured reviewsequence (default /polish --nested), then open a draft PR…
builder
Detect a project's stack and recommend or apply the universal mechanical quality guards from planwright's core catalog (formatter, linters, type-checker, test runner, secret scan, commit hooks, CI gate), plus the growable breadth dimensions. Escalates stake-bearing decisions (auth, data modeling, security posture…
spec-walkthrough
Render a spec bundle (or a chosen slice) into a plain-language, didactic comprehension artifact a human reads and judges for themselves: an unaided cold read before kickoff, re-orientation mid-execution, or onboarding to a finished or abandoned spec. Standalone and strictly read-only: it renders any status, never…
drain
Run the on-demand drain pass over every spec bundle's Gate deferral entries: evaluate structured GATE(when:) conditions, surface date and free-text gates, report malformed ones, inventory each live bundle's [manual] test-spec entries, and surface the observations log's unmined state. Read-only; nothing is…
orchestrate
Advance one planwright spec by one step: pick the next ready unit critical-path-first (or a cohesion bundle), run the freshness gate, record the dispatch under the per-spec lock, and dispatch /execute-task via the backend. A stateless, disposable control tower; a reconcile sweep rebuilds from disk. Never merges, marks…
spec-draft
Interactively elicit a four-file spec bundle (requirements.md, design.md, tasks.md, test-spec.md) at Status Draft on the spec's own branch, mining seed sources (pending notes, the observations log, transcripts) and citing them. Runs fold-detection against existing specs on every invocation and surfaces an extend…