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 arozumenko/sdlc-skills --skill define-personasgit clone --depth 1 https://github.com/arozumenko/sdlc-skillsWrote 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/arozumenko/sdlc-skills/define-personas)<a href="https://agentmods.dev/skills/arozumenko/sdlc-skills/define-personas"><img src="https://agentmods.dev/badge/skills/arozumenko/sdlc-skills/define-personas/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/arozumenko/sdlc-skills/define-personas"><img src="https://agentmods.dev/badge/skills/arozumenko/sdlc-skills/define-personas.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00139 | $0.00945 |
| Opus 5 | $0.00069 | $0.00473 |
| Sonnet 5 | $0.00028 | $0.00189 |
| Haiku 4.5 | $0.00014 | $0.00094 |
Grade A, and why
define-personas 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 11d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
define-personas
Journeys, BDD scenarios, and hypotheses all name actors. Without one canonical card per actor, the names drift ("Admin" vs "Workspace Admin" vs "Amin"), scope questions become unanswerable ("is provisioning the admin's job or the operator's?" is a persona question), and every artifact re-describes its user from scratch.
Audience calibration: the product owner is a senior product professional — this is not a persona workshop and needs no method guidance. It is a filing surface: their persona knowledge, written once, referenceable forever by slug.
The card
One file per persona: docs/discovery/personas/<slug>.md, from assets/persona-template.md. Slugs are kebab-case and canonical (team-lead, workspace-admin) — once minted, other artifacts reference them, so renames are breaking changes and deserve the same care as an ID change.
Seeding (first run)
The journeys already imply the cast, and .agents/profile.md plus the project's docs/ name the rest. Propose the card list before writing anything, drawn from:
- The seed cast named in
.agents/profile.md/ the project'sdocs/(slug, name, surface, one-liner) — the adopter's declared starting roster. - Actors extracted from every journey in
docs/discovery/journeys/, the BDD scenarios (if present), and the hypotheses.
Keep a data-subject persona whenever personal data flows through the product (pairs with the project's compliance guardrails): the person whose data the platform processes even though they never sign in. Making them a card turns the privacy question ("what does this feature mean for the data subject?") into a routine lookup instead of an afterthought.
Rules
- Every claim is evidenced or labeled. A goal/pain cites a journey, interview, or
docs/discovery/evidence/page — or carries(assumption). Cards full of unlabeled assumptions are fiction with a nice layout; the labels tellstakeholder-interviewprepare mode what to go validate. - App surface is mandatory. Its value comes from the surfaces this product owns (from
.agents/profile.md/ the project'sdocs/, plusnone) — most scope-boundary confusion is "right feature, wrong surface," and the persona card is where that gets settled once. - Fix drift when you see it. If artifacts spell an actor inconsistently, align them to the card's slug — inline, as found.
- Personas don't multiply. A new card needs a genuinely distinct goal-set, not a job-title variation. When in doubt, add a variant note to an existing card.
- Confirm before writing. Propose the cast; create files only on the PO's go. Right after each card is written — a write worth not losing to a mid-batch interruption — invoke the
memoryskill's Log op noting which card was just filed, so work resumes cleanly if the session breaks here.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 48 lines · 139 tokens per session scan A ed17679d2f71
define-personas is a skill published in the GitHub repository arozumenko/sdlc-skills (20 stars, last pushed yesterday), licensed MIT. It adds 139 tokens to every session and 945 once invoked, about $0.0007 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.