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 neat-technologies/neat --skill extendgit clone --depth 1 https://github.com/neat-technologies/neatWrote 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/neat-technologies/neat/extend)<a href="https://agentmods.dev/skills/neat-technologies/neat/extend"><img src="https://agentmods.dev/badge/skills/neat-technologies/neat/extend/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/neat-technologies/neat/extend"><img src="https://agentmods.dev/badge/skills/neat-technologies/neat/extend.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 | $0.00106 | $0.01160 |
| Opus 5.5 | $0.00042 | $0.00464 |
| Sonnet 5.5 | $0.00021 | $0.00232 |
| Haiku 4.5 | $0.00011 | $0.00116 |
Grade A, and why
extend-skill 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 1mo 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/neat extend skill contract
/neat extend exposes NEAT's instrumentation surface to the user's MCP-capable agent as surgical tools. The agent provides intelligence; NEAT provides scoped, reversible primitives. This contract supersedes ADR-081's standalone-CLI and operator-LLM-key portions per ADR-086.
1. Six tools, two roles
Diagnostic (read-only): neat_list_uninstrumented(project), neat_lookup_instrumentation(library, installed_version?), neat_describe_project_instrumentation(project).
Operative (mutate the instrumentation surface): neat_apply_extension(library, instrumentation_package, version, registration_snippet), neat_dry_run_extension(...), neat_rollback_extension(library).
Each operative tool does exactly one thing. No macro tool applies multiple extensions in one call.
2. NEAT holds no LLM key; the agent reasons
There is no NEAT_LLM_API_KEY and no LLM call originating from NEAT during the skill's execution. Registry hits resolve deterministically through the registry loader (see instrumentation-registry.md). Registry misses are reasoned about by the agent's own model; the agent drafts a proposal and the user confirms via neat_dry_run_extension before any neat_apply_extension call.
3. No standalone CLI variant
Users without an MCP agent get the deterministic npx neat.is install. Extension requires an MCP-capable agent. There is no npx @neat.is/instrument fallback.
4. File-scope restricted
Operative tools modify only instrumentation*.ts / otel-init*, .env.neat, package.json, and the lockfile (via the project's package manager). Any write attempt outside this surface returns an error.
5. Idempotent, reversible, observable
apply called twice with the same args is a no-op the second time. Every apply logs its diff to ~/.neat/extend-log.ndjson so rollback can undo it. Apply returns the exact files touched, deps added, and install-command output.
6. NEAT never auto-applies
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.
- 1mo ago First seen · 59 lines · 106 tokens per session scan A e3e93577205f
extend-skill is a skill published in the GitHub repository neat-technologies/neat (22 stars, last pushed 2d ago), licensed Apache-2.0. It adds 106 tokens to every session and 1,160 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-04.
Other skills, from other repositories
phoenix-observability
Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights.
trulens-instrumentation
Instrument LLM apps with TruLens OTEL-based tracing - from setup to debugging and optimization.
observability
Use when instrumenting a service from the inside so an incident can be explained from telemetry alone — wiring OpenTelemetry logs, metrics and traces, standing up a Collector, exporting via OTLP, and defining telemetry-driven alerts. NOT outside-in uptime probes, on-call rotation, or who-gets-paged (that is…
incident-investigation
Correlate PagerDuty incidents with Jira tickets and recent ArgoCD deployments to accelerate root cause analysis. Orchestrates multiple agents to build a timeline of events. Use when investigating active incidents, performing post-mortems, or correlating alerts with changes.
otel-profiles
OpenTelemetry profiles signal and the eBPF profiler (otelcol-ebpf-profiler, profiling receiver). Use when setting up continuous profiling with OpenTelemetry, deploying the eBPF profiler on Linux hosts, Docker, or Kubernetes (DaemonSet, kind, k3d), building a profiles pipeline, sending OTLP profiles to Pyroscope…
ase-code-lint
Lint source code for potential code quality problems. Use when the user wants to "lint" or "check" source code.