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 agentmods add skills/nullphase-net/enfurbish/nextnpx skills add nullphase-net/enfurbish --skill nextgit clone --depth 1 https://github.com/nullphase-net/enfurbishWrote 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/nullphase-net/enfurbish/next)<a href="https://agentmods.dev/skills/nullphase-net/enfurbish/next"><img src="https://agentmods.dev/badge/skills/nullphase-net/enfurbish/next.svg" alt="Measured on agentmods" 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 | $0.00043 | $0.00726 |
| Opus 5 | $0.00022 | $0.00363 |
| Sonnet 5 | $0.00009 | $0.00145 |
| Haiku 4.5 | $0.00004 | $0.00073 |
Grade A, and why
next scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/next — manual NEXT_SESSION read
Use when the user wants to pick up where the last session left off and either the SessionStart hook didn't surface anything, was disabled, or the user wants to re-consult later in the session.
Procedure
-
Find the handoffs. The skill's lib scripts live at the plugin root, two levels up from this SKILL.md. Use the base directory Claude told you about for this skill:
bun run "<skill-base-dir>/../../lib/handoffs.ts" --cwd "$(pwd)"The report lists every
NEXT_SESSION.mdunder the project root, newest first,*on the newest and[local]on the one in the current cwd. Read the header line before anything else — it names the count and, when the local pointer is not the newest, how far behind it is. -
Read the pointer the report marks
*. Not the local one, unless they are the same file. Cwd varies between sessions in one project — an autonomous run in a subdirectory writes its own handoff — and reading the cwd-local file because it was closest is what cost a session real turns on 2026-08-18.- If the local file is not the newest, say so in one line before summarizing: which file you read, and how much staler the local one is.
- If there are no handoffs at all: tell the user nothing is staged and stop. Don't synthesize a follow-up plan from thin air.
-
Summarize "Start here" and "Open threads" in 2-3 sentences.
- Mention the wrap timestamp from the file header so the user knows how stale it is.
- An item the last session flagged as untested is a hypothesis, not a finding. Present it as one — never as a settled result.
-
Ask the user which thread to pick up.
- Don't start work yet. Wait for them to choose.
What this skill does NOT do
- Write or modify any file.
/nextis read-only by design. - Touch the tooling journal or retro files.
Edge cases
+Nh after headeron a line means the file moved after its own**Last wrapped:**header was written — mid-session reconciles the header does not describe. Trust the content over the header timestamp.stamp:editedmeans the file no longer matches the stamp/wrapwrote — someone hand-edited it since. Worth mentioning; hand-written items are usually the most load-bearing ones.stamp:assistantmeans it is exactly as the last wrap left it.- If
NEXT_SESSION.mdexists but is empty or has no## Open threadsitems, treat it as "stale stub" — tell the user it exists but holds nothing actionable. - If the file is over ~16KB, summarize aggressively rather than reading the whole thing back. Long handoff files are a smell; flag it. Read the "Don't forget" section in full regardless — that section is where hard-won gotchas live, and a 2026-08-16 session spent two days re-deriving a fact staged there.
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.
- 3d ago First seen · 42 lines · 43 tokens per session scan A 6b533ed6d9ee
next is a skill published in the GitHub repository nullphase-net/enfurbish (1 stars, last pushed 16d ago), licensed MIT. It adds 43 tokens to every session and 726 once invoked, about $0.0002 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
import
Import a self-contained NeatContext context bundle shared by another person, or reconcile a newer copy of a context already on this machine, leaving the source bundle unchanged. Use only when the user explicitly invokes this skill or asks to import a NeatContext bundle.
save
Save durable decisions, findings, plans, and implementation knowledge from the visible Codex conversation into a new or existing NeatContext context. Use only when the user explicitly invokes this skill or asks to preserve the current conversation as reusable context.
create
Create a fresh NeatContext context from a user-defined behavioral profile and an existing local knowledge folder. Use only when the user explicitly invokes this skill or asks to create a new context rather than save the current conversation.
extensions
Report which extensions the connected NeatContext context expects, and whether this machine provides them. Use when the user asks what a context can reach, why an extension tool is missing, or how to connect one here.
delete
Preview and permanently delete a NeatContext context while preserving any externally linked knowledge folder. Use only when the user explicitly invokes this skill or clearly asks to delete a context.
export
Export a NeatContext context saved from a conversation into a self-contained bundle folder that can be shared or moved to another machine. Use only when the user explicitly invokes this skill or asks to export a NeatContext context.