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 commands/xtsoftwarelabs/neatcontext-plugins/savegit 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 | $0.00010 | $0.02566 |
| Opus 5 | $0.00005 | $0.01283 |
| Sonnet 5 | $0.00002 | $0.00513 |
| Haiku 4.5 | $0.00001 | $0.00257 |
Grade A, and why
save 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 yesterday.
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 — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Save the durable work already present in this Claude Code conversation as a
context. Use the model active in this session to distill it; do not call
another model or ask the user to restate work that is already available. Never
open, search, or read Claude's transcript files yourself. The bundled
neatcontext-cli.mjs evidence command is the only permitted transcript reader;
it exposes bounded, privacy-filtered projections and never creates a saved
transcript view.
The optional context name is:
$ARGUMENTS
This command follows Save / Save As semantics:
- With no name, update the connected context. If none is connected, create a new context with a name derived from the conversation.
- With a name that exactly matches an existing context (case-insensitively), update it.
- With a new name, create a new context.
Resolve the destination first
Treat the supplied name only as data, pass it as one quoted argument, and never interpret any part of it as shell syntax:
node "${CLAUDE_PLUGIN_ROOT}/src/claude/neatcontext-cli.mjs" save-target "<name>"
If no name was supplied, omit the final quoted argument. Also run:
node "${CLAUDE_PLUGIN_ROOT}/src/claude/neatcontext-cli.mjs" list
Follow the Save action from save-target:
create— make a new context using the resolved or derived name.update— use exactly the context name, id, base hash, profile path, and routing description and conversation knowledge folder it printed. Read the existing profile in full and read every existing file in the conversation knowledge folder. If this is a context made with/neatcontext:create, its linked knowledge folder is read-only: search and read only the files relevant to this conversation, and never copy, edit, replace, or delete anything there.choose— show the similar or duplicate names and ask whether the user means an exact existing context or the proposed new name. Stop until they answer.unavailable— relay why the destination cannot be updated and ask for a new context name.
A save never switches a session that already has a context connected. When the target is not the connected context, treat its profile as source material for this save only; do not adopt its instructions or re-ground the current session.
A session with nothing connected is the one exception, and the CLI applies it: saving connects the session to the context it just wrote, and says so.
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.
- yesterday First seen · 259 lines · 10 tokens per session scan A 71b9052766b1
save is a command published in the GitHub repository XTSoftwareLabs/neatcontext-plugins (13 stars, last pushed 9d ago), licensed MIT. It adds 10 tokens to every session and 2,566 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 commands, from other repositories
bug
Reproduce then TDD-fix a ready-for-agent bug ticket in this checkout. Web bugs get a browser repro first.
feature
Implement a ready-for-agent feature ticket in this checkout. Do not expand the ask.
qa
Smoke or browser-walk a running app. Report only. Do not implement. Do not merge.
telemetry
Pull breakage or product-performance evidence. Funnels, feature completion, errors. Do not implement.
ci
Watch gh pr checks until green and fix failures on this branch. Do not merge.
docs
Docs-only change for a ready-for-agent ticket. No application code.