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 ztemerbekov/a1-marketing-skills --skill a1-wayfindergit clone --depth 1 https://github.com/ztemerbekov/a1-marketing-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/ztemerbekov/a1-marketing-skills/a1-wayfinder)<a href="https://agentmods.dev/skills/ztemerbekov/a1-marketing-skills/a1-wayfinder"><img src="https://agentmods.dev/badge/skills/ztemerbekov/a1-marketing-skills/a1-wayfinder/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/ztemerbekov/a1-marketing-skills/a1-wayfinder"><img src="https://agentmods.dev/badge/skills/ztemerbekov/a1-marketing-skills/a1-wayfinder.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 | $0.00039 | $0.01503 |
| Opus 5.5 | $0.00016 | $0.00601 |
| Sonnet 5.5 | $0.00008 | $0.00301 |
| Haiku 4.5 | $0.00004 | $0.00150 |
Grade A, and why
a1-wayfinder 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 2mo 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wayfinder
Turn a marketing effort that is too large and foggy for one conversation into one shared decision map. Find the way to the destination; do not execute the destination itself.
Use two modes:
- Chart when the user brings a loose marketing initiative without a map.
- Continue when the user supplies or identifies an existing Wayfinder map.
Keep one map as the complete source of truth. Represent work as decision questions inside that document, not as tracker issues, project tasks, labels, assignments, or a separate backlog.
Decision ownership
Distinguish facts, recommendations, and decisions:
- Establish discoverable facts from supplied material or reliable sources.
- Give a concrete recommendation when judgment is needed.
- Treat a consequential choice about audience, positioning, promise, budget, risk, or brand as resolved only when the user confirms it or supplied authority already settles it.
Record uncertainty and material disagreement. Never turn an assumption, recommendation, or plausible market convention into a confirmed decision.
Plan, don't execute
Wayfinding ends when nothing material remains to decide before a downstream skill or team can create the destination. A cheap research pass, comparison, outline, message sketch, or other disposable prototype may support a decision; it is evidence, not the destination.
Resolve at most one decision in a Continue run. Charting creates the map and stops before resolving its first decision.
Shared map
Read the map format whenever creating or updating a map. Keep the destination, decisions, frontier, blocked questions, fog, and out-of-scope boundary in one document.
Use the user's named writable document when provided. Otherwise, if a writable workspace is available, create wayfinder-<short-topic>.md at its root. Use a short lowercase hyphenated topic and avoid overwriting an existing file. If no writable workspace exists, return the complete map in the conversation so the user can save and supply it later.
What ships with it
6 files 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.
- 2mo ago First seen · 88 lines · 39 tokens per session scan A aac864e97017
a1-wayfinder is a skill published in the GitHub repository ztemerbekov/a1-marketing-skills (8 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 1,503 once invoked, about $0.0002 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 2026-08-31.
a1-wayfinder compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| a1-wayfinderztemerbekov/a1-marketing-skills | Skill | 8 | 1mo ago | MIT | A | 39 | Claude Code, Codex |
| deai_humanizemateaix/mateclaw | Skill | 1.2k | 2d ago | Apache-2.0 | A | 82 | Claude Code, Codex |
| analytics-strategyrampstackco/claude-skills | Skill | 1.0k | 11d ago | MIT | A | 126 | Claude Code |
| cro-optimizationrampstackco/claude-skills | Skill | 1.0k | 11d ago | MIT | A | 123 | Claude Code |
| communityericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 77 | Claude Code, Codex |
| newsletterericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 80 | Claude Code, Codex |
| research-seo-demandtsingyuai/growth-lab | Skill | 2.0k | 1mo ago | Apache-2.0 | A | 102 | Codex |