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 voxpelli/vp-claude --skill nudgegit clone --depth 1 https://github.com/voxpelli/vp-claudeWrote 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/voxpelli/vp-claude/nudge)<a href="https://agentmods.dev/skills/voxpelli/vp-claude/nudge"><img src="https://agentmods.dev/badge/skills/voxpelli/vp-claude/nudge/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/voxpelli/vp-claude/nudge"><img src="https://agentmods.dev/badge/skills/voxpelli/vp-claude/nudge.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 | $0.00210 | $0.02389 |
| Opus 5 | $0.00105 | $0.01195 |
| Sonnet 5 | $0.00042 | $0.00478 |
| Haiku 4.5 | $0.00021 | $0.00239 |
Grade A, and why
nudge 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 8d 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nudge
Manage the Claude Code feature-adoption nudge cycle against the Basic Memory
note main/reference/claude-code-noteworthy-features. Two modes on the same
data (same note, same cache, same contract):
- Bare
/nudge(or no argument) → Mode A (sync). Re-read the note, filter out adopted/declined features, and regenerate the tip cache. /nudge check→ Mode B (adoption check). Scan transcripts for real feature-use evidence, preview status transitions, write approved changes to the note's frontmatter, then regenerate the same cache.
Route by the argument: no argument / sync phrasing → Mode A; check / adoption
phrasing → Mode B.
Intentionally Claude-Code-specific, not a template for a generic mechanism.
This skill hardcodes the note permalink
(main/reference/claude-code-noteworthy-features) and Claude-Code slug
vocabulary — a deliberate, stated exception to this project's general
domain-generic-skill convention, because the whole task is specifically about
Claude Code feature adoption.
The single rule and line grammar both modes share when regenerating the cache
live in references/tip-cache-contract.md —
the single source of truth, so the two independent write paths never drift.
Mode A: sync
Follows the same vendor-sync pattern as tag-sync: registry (BM note) → fetch
via MCP → filter → write to a synced local file the SessionStart hook
(hooks/tip-fragment.sh) reads without ever touching Basic Memory. Always
re-fetches on invocation — no same-day guard (read_note is one cheap call and
the hook already throttles tip display to once/day independently).
Step 1: Fetch the note
mcp__basic-memory__read_note(
identifier="main/reference/claude-code-noteworthy-features",
output_format="json",
include_frontmatter=true
)
On failure or an empty/malformed result, report the error and exit without
writing — never overwrite a working cache with partial content. A missing note
is reported, never auto-created (that's /intel's kind of job, not this
skill's). Zero [nudge] observations is a legitimate state — write an empty
cache file.
What ships with it
3 files 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.
- 8d ago First seen · 214 lines · 210 tokens per session scan A d53674a8ecff
nudge is a skill published in the GitHub repository voxpelli/vp-claude (3 stars, last pushed 11d ago), licensed MIT. It adds 210 tokens to every session and 2,389 once invoked, about $0.0011 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
harden-memories
Audit the bd remember store and recommend which entries to prune, so each one earns its per-session bd prime injection cost. Read-only: it proposes a triage table plus the exact bd forget / migration commands; you run them. Use when bd remember entries have accumulated, feel stale, redundant, or conflicting, or when…
synergy-tracker
Manage cross-project synergy tracking between sibling projects. Use when the user wants to log a shared pattern, a divergence, an extraction candidate, or something a sibling project has that this one doesn't. Also use when the user wants to promote synergy entries to Basic Memory (workflow 5). NOT for upstream…
upstream-tracker
Manage upstream issue tracking for this project. Use when the user wants to log a bug or friction point in a vendor package or npm dependency, review open upstream items, resolve a tracked issue, run a trend review, generate the upstream observations section of a sprint retrospective, promote upstream observations to…
retrospective
Run a sprint retrospective for this project. Use when the user says 'retrospective', 'retro', 'close out the sprint', 'what went well', 'generate retro', or wants to generate a RETRO-NN.md file. Reads UPSTREAM-.md files, recent git history, and conversation context to pre-populate the retrospective. Do NOT use for…
backlog-groomer
Manage the beads backlog for this project. Use when the user wants to review or triage open issues, reprioritize the backlog, identify obsolete issues to close, investigate a topic to inform future work, create new issues from research findings, or enrich an existing issue with external context. Trigger phrases…
swarm-wave
Orchestrate multi-agent development sprints with wave-based parallelism. Use when the user wants to plan a swarm sprint, partition work into file-disjoint waves, map file contention across open issues, run a post-wave quality gate with review agents, manage agent backpressure, run a parallel research wave, or…