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 RockyHong/super-bootstrap --skill journey-simulationgit clone --depth 1 https://github.com/RockyHong/super-bootstrapWrote 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/rockyhong/super-bootstrap/journey-simulation)<a href="https://agentmods.dev/skills/rockyhong/super-bootstrap/journey-simulation"><img src="https://agentmods.dev/badge/skills/rockyhong/super-bootstrap/journey-simulation/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/rockyhong/super-bootstrap/journey-simulation"><img src="https://agentmods.dev/badge/skills/rockyhong/super-bootstrap/journey-simulation.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 | $0.00079 | $0.03199 |
| Opus 5 | $0.00039 | $0.01599 |
| Sonnet 5 | $0.00016 | $0.00640 |
| Haiku 4.5 | $0.00008 | $0.00320 |
Grade A, and why
journey-simulation 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 8d 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
journey-simulation
Overview
Spawn isolated subagent to execute a real task under identity-as-fact briefing + sandbox spec. Subagent never knows it's observed. Gateway extracts funnel post-hoc from narration.
Persona is a distribution, not a single person. Persona-slug names a group; subagent samples one path. Read each waypoint as "how thinned is this group?" — not "did this individual finish?" Funnel attrition is the unit of signal.
When to use
- Caller asks to "simulate a user", "test our flow", "will users get stuck on X", "cognitive walkthrough", "cold-eyes review"
- Pressure-testing a flow before real-user testing or after a redesign
- Reviewing whether a doc / README / game loop / future-self artifact is comprehensible cold
Skip when: caller wants ground-truth real-user data (use real-user testing); caller wants design recommendations (this skill observes, doesn't prescribe).
Phase 0 — Clarify & de-bias
Run before dispatch. Caller-in-loop. Never skipped.
- Ask: what artifact, what flow, desired outcome of this test, your concern / hypothesis?
- Surface caller's bias: "you suspect X — the sim must not be primed to find X. Restate inputs in neutral terms."
- Ask: realistic personas (not aspirational ICP)? Skeptic / return / negative cases worth running?
- Curate: strip project jargon, success-bias, design rationale, vision-statement leakage.
- Structural-cue check: if curated persona reads as constructed (over-precise biographic detail, hyper-specific multi-constraint situations, obscure personal history), loosen toward naturalistic under-specification.
- Show curated AND stripped versions side-by-side. Caller picks curated, stripped, or correction. Single-stage curation = bias not fully surfaced. Both versions visible to caller is the load-bearing step.
- Capture bullseye + hypothesis privately. Held only by gateway. Never enters subagent prompt.
Phase 1 — Input contract
Required inputs (free-form shape, must hit minimum bar each):
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.
- 8d ago First seen · 216 lines · 79 tokens per session scan A 8666c3c2428b
journey-simulation is a skill published in the GitHub repository RockyHong/super-bootstrap (3 stars, last pushed today), licensed MIT. It adds 79 tokens to every session and 3,199 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 2026-08-31.
Other skills, from other repositories
playwright-e2e
Skill "playwright-e2e" from lukasrepublic/agentic-foundry, covering when to trigger, procedure, inputs, outputs and quality bar.
sd-test
The disciplined test-recipe gate the generic agent runs for the software-delivery TEST step (/foundry:sd-test, step 8). A PROCEDURE — invoke the MERGED foundry-verify.py executor, read the run record's records whose phase == "testrecipe" (unit / integration / e2e), surface the profile's numeric coveragegate and advise…
accessibility-checks
Use when verifying accessibility (WCAG 2.2 AA) of a rendered UI in a real browser before reporting done — the omp-native replacement for the chrome-devtools a11y plugin. Runs a concrete ordered checklist with omp's builtin browser tool (open tab → tab.evaluate DOM query / elementFromPoint / getComputedStyle /…
ui-verify-checks
Use when verifying a frontend UI change in a real browser before reporting done. The canonical 7-check list (real auth → render≠behavior → scroll containment → primary-button reachability → selection-state sync → responsive → console) + environment fail-fast rule (transport-unreachable vs HTTP error distinction) +…
test-fixture-creation
Guidelines for creating unbiased test fixtures that integrate with project infrastructure. Use when creating fixtures for manual testing, setting up E2E test scenarios, or building code samples with deliberate issues for LLM review. Ensures fixtures work with hook automation and pass Phase 1 checks.
chrome-verify-checks
Use when verifying a chrome-extension/ change before reporting done. The canonical 7-check list (build → Service Worker vm.createContext compat → manifest sanity → per-site content-script DOM contract → message-passing trace → test suite → manual-load checklist) + verdict rules. chrome-extension/ is a strong-guard…