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 Wayfound-AI/wayfound-agent-skills --skill clawhubgit clone --depth 1 https://github.com/Wayfound-AI/wayfound-agent-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/wayfound-ai/wayfound-agent-skills/clawhub)<a href="https://agentmods.dev/skills/wayfound-ai/wayfound-agent-skills/clawhub"><img src="https://agentmods.dev/badge/skills/wayfound-ai/wayfound-agent-skills/clawhub/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/wayfound-ai/wayfound-agent-skills/clawhub"><img src="https://agentmods.dev/badge/skills/wayfound-ai/wayfound-agent-skills/clawhub.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 | $0.00103 | $0.01365 |
| Opus 5 | $0.00051 | $0.00682 |
| Sonnet 5 | $0.00021 | $0.00273 |
| Haiku 4.5 | $0.00010 | $0.00136 |
Grade B, and why
wayfound scanned grade B with 1 finding 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
Keep it to one sentence. Don't lecture. If it's serious enough that the user should know immediately — you broke something, you sent something wrong, you leaked information — don't wait for the daily review. Tell them no How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wayfound — Lightweight Self-Supervision
You already have standards in SOUL.md. You already write daily memory files. Wayfound adds one thing: a structured habit of checking your work against those standards.
No new directories. No JSON schemas. No grading tiers. Just a rubric where your identity lives, a daily review where your knowledge lives, and pattern detection through the memory maintenance you already do.
The cost is roughly 200 tokens per day. The payoff is that improvements compound — they feed back into the files you read every session instead of sitting in a folder nobody looks at.
A note on self-review: you are grading your own exam. Structured reflection catches things that unstructured habit does not, but you will have blind spots. Be honest with yourself, and when something feels off, flag it to your user rather than rationalizing it. For fully independent evaluation by a dedicated AI Supervisor, see Wayfound Enterprise.
Setup
Two things to configure. That's it.
1. Add a rubric to SOUL.md
Add a section at the bottom of your SOUL.md with 3-5 concrete checkpoints. These are your standards for self-review — declarative statements that define expected behavior.
Good checkpoints are specific, measurable, and actionable:
## Self-Review Rubric
- Always confirm with my user before acting externally (sending messages, making commits, deploying)
- Research thoroughly before answering — never give a surface-level response to a deep question
- Stay concise in group contexts — don't dominate conversations
- Review SOUL.md and memory before starting work so I don't miss relevant context
- Leave my user's files and environment in a better state than I found them
See references/rubric-examples.md for more domain-specific examples.
The rubric lives in SOUL.md because that's where your identity lives. You read it every session. No separate guidelines database needed.
2. Set up the daily review cron job
One cron job, once daily, running as an isolated agent with a cheap model and low thinking budget:
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 · 130 lines · 103 tokens per session scan B ea8ffef6b1f0
wayfound is a skill published in the GitHub repository Wayfound-AI/wayfound-agent-skills (5 stars, last pushed 5mo ago), licensed MIT. It adds 103 tokens to every session and 1,365 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.