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 SaikaAco/saika-hermes-skills --skill wfgit clone --depth 1 https://github.com/SaikaAco/saika-hermes-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/saikaaco/saika-hermes-skills/wf)<a href="https://agentmods.dev/skills/saikaaco/saika-hermes-skills/wf"><img src="https://agentmods.dev/badge/skills/saikaaco/saika-hermes-skills/wf/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/saikaaco/saika-hermes-skills/wf"><img src="https://agentmods.dev/badge/skills/saikaaco/saika-hermes-skills/wf.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 | $0.00085 | $0.02154 |
| Opus 5.5 | $0.00034 | $0.00862 |
| Sonnet 5.5 | $0.00017 | $0.00431 |
| Haiku 4.5 | $0.00009 | $0.00215 |
Grade A, and why
wf 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 — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WF — Wayfinder Flow
Purpose
WF is the short entry point and ambiguity router for the full decision-to-work system:
facts unclear -> evidence handler / research
human choice unclear -> Bounded Grilling (`clarify`, one question)
interaction unclear -> `/prototype` + human reaction
many dependent unknowns -> Wayfinder LIGHT or FULL
route settled -> To-Spec when a contract is needed
approved spec needs decomposition -> `/to-tickets`
execution needs durability -> separately authorized Kanban
Manual invocation is /wf. Automatic invocation follows the standing user
instruction: when work contains genuine doubt or something required is unclear,
do not silently assume; investigate discoverable facts, then ask the human
through this flow when a human-owned value remains.
Trigger gate
Invoke WF automatically before proceeding when at least one unresolved item can change the action, output, safety, or acceptance and any of these holds:
- two or more reasonable interpretations remain;
- a required value, scope boundary, destination, priority, or success condition is missing or ambiguous;
- authority for a mutation, publication, cost, credential use, cleanup, irreversible step, or cross-profile action is unclear;
- sources or instructions materially contradict one another;
- the applicable artifact, environment, target, owner, or backend cannot be identified confidently;
- a human preference or trade-off is being treated as if it were a factual lookup;
- the work would require inventing acceptance criteria, an exception, or an unsupported assumption;
- interaction with a concrete artifact is needed to judge logic or UI.
Do not manufacture doubt. WF is not required when one interpretation is plainly supported by the current request, authoritative project convention, and observable evidence. A discoverable fact is not automatically a user question: look it up first. An obvious default supported by current evidence is not a silent assumption; state it when material and proceed under the original authority.
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 · 247 lines · 85 tokens per session scan A 1110e775a9a8
wf is a skill published in the GitHub repository SaikaAco/saika-hermes-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 85 tokens to every session and 2,154 once invoked, about $0.0003 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.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
motion-frames
A single-frame motion-design composition with looping CSS animations — rotating type ring, animated globe, ticking timer, parallax labels. Renders as a hero video poster you can hand straight to HyperFrames or any keyframe-based exporter. Use when the brief asks for "motion design", "animated hero", "loop", "video…
webgl-halftone-drift
A self-contained WebGL2 hero: a flowing field screened through a rotated halftone dot grid into a duotone print aesthetic; move the cursor to bend the drift.
motion-future
The Future Is Already Here — motion design template. A 20-second electric-blue tech reel, rebuilt from the viral original: 3D cubes, a word tunnel, liquid chrome type, a FUTURE.EXE desktop, a countdown, glass objects and a chrome FUTURE hero, cut to 120 BPM.
motion-kinetic-motion-designer
A motion-design business-card animation that teaches movement through bouncing, lettering, action words, timing curves, trails, and anticipation. Anticipation is a small preparatory movement before the main action.
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).