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 bjorn-ingmanson/thefroject-plugins --skill feature-adoption-coachgit clone --depth 1 https://github.com/bjorn-ingmanson/thefroject-pluginsWrote 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/bjorn-ingmanson/thefroject-plugins/feature-adoption-coach)<a href="https://agentmods.dev/skills/bjorn-ingmanson/thefroject-plugins/feature-adoption-coach"><img src="https://agentmods.dev/badge/skills/bjorn-ingmanson/thefroject-plugins/feature-adoption-coach/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/bjorn-ingmanson/thefroject-plugins/feature-adoption-coach"><img src="https://agentmods.dev/badge/skills/bjorn-ingmanson/thefroject-plugins/feature-adoption-coach.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 | $0.00069 | $0.01107 |
| Opus 5 | $0.00034 | $0.00553 |
| Sonnet 5 | $0.00014 | $0.00221 |
| Haiku 4.5 | $0.00007 | $0.00111 |
Grade A, and why
feature-adoption-coach 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature Adoption Coach
Connect new Claude Code features to the user's actual workspace. Generic "here's what's new" lists don't change behavior — workspace-specific adoption plans do.
Gather Context First
- Find recent feature reports in
outputs/feature-watch/if present (most recent first) - If none, fetch the latest entries from the Anthropic Claude Code changelog
- Inventory the user's workspace — what's currently in
.claude/(skills, commands, agents, hooks, settings.json) - Read
CLAUDE.mdfor project type and conventions - Identify which features the user is actively using (recent file edits in
.claude/are a signal)
The Adoption Sequence
Step 1 — Inventory current state
For each Claude Code primitive, mark what exists:
| Primitive | Files present | Recent activity |
|---|---|---|
| Skills | Count + categories | Modified in last 30 days? |
| Commands | Count + active ones | Modified in last 30 days? |
| Agents | Count + tool restrictions | Modified in last 30 days? |
| Hooks | Active vs disabled | Any new hooks since setup? |
| MCP servers | Configured count | Any unused? |
| Settings | Permissions, env vars | Custom or default? |
This baseline determines what adoption looks like.
Step 2 — Score each new feature for fit
For every feature in the report, score 0-3 against three lenses:
| Lens | Question | Score |
|---|---|---|
| Fit | Does this solve a problem the user already has? | 0-3 |
| Effort | How long to adopt? (0=hours, 3=days) | 0-3 (lower = better) |
| Reversibility | If wrong, can the user back it out? | 0-3 |
Weight: fit * 2 - effort + reversibility. Highest scores are the picks.
Step 3 — Categorize each feature
Sort matched features into:
- Quick win — high fit, low effort. Adopt now.
- Medium investment — high fit, multi-day effort. Plan for next week.
- Speculative — interesting but unclear fit. Bookmark for the next /feature-watch run.
- Skip — doesn't match the workspace or duplicates existing setup.
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 · 126 lines · 69 tokens per session scan A 6f88c82e341b
feature-adoption-coach is a skill published in the GitHub repository bjorn-ingmanson/thefroject-plugins (1 stars, last pushed 2mo ago), licensed MIT. It adds 69 tokens to every session and 1,107 once invoked, about $0.0003 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
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…
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…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.