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 tsai09495/matt-pocock-engineering --skill wayfindergit clone --depth 1 https://github.com/tsai09495/matt-pocock-engineeringWrote 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/tsai09495/matt-pocock-engineering/wayfinder)<a href="https://agentmods.dev/skills/tsai09495/matt-pocock-engineering/wayfinder"><img src="https://agentmods.dev/badge/skills/tsai09495/matt-pocock-engineering/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/tsai09495/matt-pocock-engineering/wayfinder"><img src="https://agentmods.dev/badge/skills/tsai09495/matt-pocock-engineering/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 | $0.00035 | $0.01444 |
| Opus 5 | $0.00017 | $0.00722 |
| Sonnet 5 | $0.00007 | $0.00289 |
| Haiku 4.5 | $0.00003 | $0.00144 |
Grade A, and why
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 12d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wayfinder
Wayfinder pushes back the fog around a destination by resolving decisions, not by building deliverables. It is explicit-only because it creates a heavier, durable cross-session workflow.
Read:
- routing-policy.md for entry and exit routing;
- quality-baseline.md for side-effect boundaries;
- the configured
docs/agents/issue-tracker.mdfor tracker-specific map, dependency, frontier, claim, and resolve operations.
Use the current agent by default. Parallel research and ticket workers follow optional-enhancements.md.
Entry gate
Wayfinder fits only when all or most are true:
- the destination cannot be planned reliably within one agent session;
- several unknowns depend on one another;
- the work is greenfield, a huge feature, or long-range restructuring;
- ordinary grilling would consume the context before a buildable spec emerged;
- a durable map is needed across sessions or participants.
No-fog early exit
Exit before creating a map when the destination is already clear enough to specify or split. Recommend:
grill-with-docsfor a manageable set of decisions;to-specfor an already-understood destination;to-ticketsfor an already-approved plan;implementfor one bounded work item.
Being large is not enough. Wayfinder requires decision fog.
Core model
- Destination — the outcome the user wants, described without pretending the route is known.
- Map — a durable index of destination, notes, decisions so far, fog, ticket links, and current frontier.
- Fog — important unknowns or decisions that prevent a trustworthy specification.
- Decision ticket — one bounded question whose answer removes fog. It produces an answer, not a product feature.
- Blocking edge — another ticket whose answer is required first.
- Frontier — open, unclaimed tickets whose blockers are resolved.
The map is an index, not a giant document. Put detailed evidence and conclusions in ticket answers or durable linked artifacts.
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.
- 12d ago First seen · 182 lines · 35 tokens per session scan A 91569f543abd
wayfinder is a skill published in the GitHub repository tsai09495/matt-pocock-engineering (2 stars, last pushed 18d ago), licensed MIT. It adds 35 tokens to every session and 1,444 once invoked, about $0.0002 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
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.
wiki
Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.
stss
Reduce defensive disclaimers, stacked hedging, and self-protective narration in proposals and decision-facing writing. Use when the user asks to rewrite or audit a proposal, plan, research contribution, executive summary, or similar text for directness. Do not use for ordinary code work or unrelated prose.