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/xtsoftwarelabs/neatcontext-plugins/session-startnpx skills add XTSoftwareLabs/neatcontext-plugins --skill session-startgit clone --depth 1 https://github.com/XTSoftwareLabs/neatcontext-pluginsWhat 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 | $0.00027 | $0.00589 |
| Opus 5 | $0.00014 | $0.00295 |
| Sonnet 5 | $0.00005 | $0.00118 |
| Haiku 4.5 | $0.00003 | $0.00059 |
Grade A, and why
using-neatcontext 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 2d 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.
What it actually says
NeatContext runtime
NeatContext is installed for this Kimi Code session.
The current Kimi Code session id is ${KIMI_SESSION_ID}. It is an internal
routing token. Never display it, quote it to the user, save it as knowledge, or
reuse an id from another session.
Kimi Code does not pass its session id to MCP child processes. At the first
user request in this session, call the NeatContext bind_session tool with the
exact id above before answering. The tool returns the current selection and
routing menu, then replaces itself with the context-dependent tools. Call it
once per session, not per request. The bridge process can outlive the session
it was bound in, so binding this session's id also re-grounds a bridge left
over from an earlier session in the same window — the tool reports this
session's selection either way.
After binding:
- Follow the returned routing mode and menu. The plugin itself does not classify prompts; you decide whether the user's standalone request belongs to one of the listed contexts.
- In
askmode, name the matching context and ask before switching. Inautomode, switch only on a clear match and tell the user. Inmanualmode, never switch automatically. - Do not route on short replies or follow-ups that continue the current topic.
- Use
preview_contextonly when two contexts are genuinely plausible. - Once a context is selected, call
get_contextfor requests in its scope only when its result is not already present since the latest switch or compaction. Reuse current grounding instead of polling. - Read a returned profile in full, search the indicated knowledge folder, cite exact local paths used, and say when saved material does not cover the question.
Contexts are connected inside this Kimi Code session with use_context or the
explicit /neatcontext:use command. The plugin uses local Contexts; there is no
NeatContext Desktop connection right now.
The plugin commands are /neatcontext:save, /neatcontext:use,
/neatcontext:disconnect, /neatcontext:list, /neatcontext:status,
/neatcontext:create, /neatcontext:import, /neatcontext:delete, and
/neatcontext:mode. Each command delegates to a bundled skill that receives
this session id through Kimi Code's skill expansion. Use
/neatcontext:save to preserve durable work from the visible conversation;
never parse Kimi Code transcript files for that workflow.
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.
- 2d ago First seen · 52 lines · 27 tokens per session scan A 9120b17d5b81
using-neatcontext is a skill published in the GitHub repository XTSoftwareLabs/neatcontext-plugins (13 stars, last pushed 9d ago), licensed MIT. It adds 27 tokens to every session and 589 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
implement
Use when implementing a spec or GitHub ticket in this checkout.
loop-on-ci
Monitor PR checks and fix failures until green. Uses gh pr checks as the source of truth for PR-attached checks.
run-smoke-tests
Run Playwright smoke tests, debug failures, and verify fixes. Use for smoke, e2e, Playwright, or pre-ship browser verification.
pipeline
Use when the user wants a feature idea taken end-to-end in one autonomous run — phrases like "run the whole pipeline", "take this feature from idea to finished branch", "brainstorm then build it autonomously", "do everything from idea to merged", "implement all phases without stopping". Triggers when they want…
craft
Use when a product idea is still vague and needs to become a clear definition of what to build — "let's craft an app like X", "help me define what I actually want", "clarify this idea before we plan it". Also use before planning or implementation when requirements, UX, domain behaviour, or technical preferences have…
browser-use
Drive a real browser to QA a running app. Screenshots, clicks, forms, evidence. Use when there is no Playwright suite, or when a human flow must be walked.