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 jamiemill/layers-skills --skill layers-observed-behaviourgit clone --depth 1 https://github.com/jamiemill/layers-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/jamiemill/layers-skills/layers-observed-behaviour)<a href="https://agentmods.dev/skills/jamiemill/layers-skills/layers-observed-behaviour"><img src="https://agentmods.dev/badge/skills/jamiemill/layers-skills/layers-observed-behaviour/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/jamiemill/layers-skills/layers-observed-behaviour"><img src="https://agentmods.dev/badge/skills/jamiemill/layers-skills/layers-observed-behaviour.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
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 | $0.00028 | $0.00940 |
| Opus 5 | $0.00014 | $0.00470 |
| Sonnet 5 | $0.00006 | $0.00188 |
| Haiku 4.5 | $0.00003 | $0.00094 |
Grade A, and why
layers-observed-behaviour 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 10d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/layers-observed-behaviour
Assumes /layers-intro has been loaded. This skill is a library of techniques, not a script — see "How to use these skills" there.
The observed behaviour layer is the closest we can get to reality — what users actually do, not what we think they do or wish they would. Everything above it is interpretation; this layer is the source.
It splits into two situations. Detect which applies and say so:
- Plan — no research yet; design a study.
- Synthesise — research material exists; make sense of it.
With partial research, synthesise what exists first, then plan to fill the gaps.
The decisions this layer makes
- What specific questions we most need to answer about our users
- What evidence already exists, and how reliable it is
- How to gather what's missing
- What patterns hold with confidence vs. what remains assumption
Disciplines — what keeps observation honest
- Stay close to raw data. Observations should be specific and near the source — what users said, did, felt — not summarised into conclusions.
- Ground in something seen or heard, not in team beliefs.
- Mark confidence: observed / inferred / assumed. If you mark something observed, the verbatim that supports it should be quotable in the same note — an observed claim with no quotable evidence is really inferred.
- Name research gaps explicitly rather than papering over them.
- Workarounds are signal. A need real enough to motivate improvisation is a strong one.
Techniques
To plan a study
| Technique | Use it when |
|---|---|
| Define the learning goal | Always start here. Push past "understand users better" to 2–3 specific questions — "what triggers someone to refer a friend, and what makes them hesitate." |
| JTBD interviews | Understanding triggers, motivations, anxieties. Interview about a real past experience, not hypotheticals. Guide: opening ("tell me about the last time you…"), timeline (what triggered it, what you tried), motivations (what you hoped, what worried you), closing. |
| Contextual inquiry / observation | What users say differs from what they do — watch real work for tacit behaviour. |
| Diary studies | Behaviour is distributed over time or infrequent — users self-report as events occur. |
| Support ticket / review analysis | Existing product with accumulated signal — pain points at scale without recruiting. |
| Analytics review | What users do (not why). Complements qualitative; doesn't replace it. |
| Usability observation | Where people struggle or succeed with an existing product. |
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.
- 10d ago First seen · 75 lines · 28 tokens per session scan A 7f8b2692940f
layers-observed-behaviour is a skill published in the GitHub repository jamiemill/layers-skills (299 stars, last pushed 3mo ago), licensed MIT. It adds 28 tokens to every session and 940 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
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).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.