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/extensionsgit 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 | $0.00015 | $0.00370 |
| Opus 5 | $0.00008 | $0.00185 |
| Sonnet 5 | $0.00003 | $0.00074 |
| Haiku 4.5 | $0.00002 | $0.00037 |
Grade A, and why
extensions scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Report what the connected context's extensions can and cannot do here.
!node "${CLAUDE_PLUGIN_ROOT}/src/claude/neatcontext-cli.mjs" extensions
Relay the report above. Two separate things are being reported and the difference matters to the user:
- What the context expects — the extension it declares and the capability that provides. This travels with the context, and it is the same on every machine the context reaches.
- What this machine provides for it. That is local, hand-written, and lives in the bindings file the report names. Nothing configures it automatically, and nothing in a shared context can configure it.
If something is reported as not configured, show the example binding from the
report and say where the file goes. Tell them to keep credentials in the
environment and name them under envFrom, rather than writing them into the
file.
If an extension is reported as unavailable or failed, relay the reason as given — a command that is not there, a server that did not answer — and do not guess at a fix beyond what the report says.
Say plainly that the context still works: its profile and knowledge folder are served whether or not any extension is configured.
If the user wants this context to expect something new, use
neatcontext-cli.mjs extensions add <id> --capability "<what it lets this context do>", optionally with --tools a,b and --important. That records
what the context wants; it connects nothing on its own.
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 · 36 lines · 15 tokens per session scan A fe7034dc8472
extensions is a command published in the GitHub repository XTSoftwareLabs/neatcontext-plugins (13 stars, last pushed 9d ago), licensed MIT. It adds 15 tokens to every session and 370 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.