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 harness/harness-skills --skill instrument-metricgit clone --depth 1 https://github.com/harness/harness-skillsWrote 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/harness/harness-skills/instrument-metric)<a href="https://agentmods.dev/skills/harness/harness-skills/instrument-metric"><img src="https://agentmods.dev/badge/skills/harness/harness-skills/instrument-metric/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/harness/harness-skills/instrument-metric"><img src="https://agentmods.dev/badge/skills/harness/harness-skills/instrument-metric.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 | $0.00065 | $0.02675 |
| Opus 5.5 | $0.00026 | $0.01070 |
| Sonnet 5.5 | $0.00013 | $0.00535 |
| Haiku 4.5 | $0.00006 | $0.00267 |
Grade C, and why
instrument-metric scanned grade C with 1 finding 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
Confirm environment, client/server mode, and the existing environment-variable or secret-manager **reference**, not its value. SDK keys are not Harness admin API tokens; never put a server-side key in a browser bundle. T How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instrument Metric
Wire up the track() call an FME metric needs, then verify the event is actually arriving — don't declare success on code changes alone. Key = the same key getTreatment uses (attribution fact); value units must match the metric's format (ms vs s, dollars vs cents) — a wrong unit gives silently wrong results. Related: /create-metric creates metrics; /choose-metric recommends which metrics to use.
Tools
Works through the Harness MCP server or the Harness CLI; names are from tool-map.md.
| Operation | MCP | CLI |
|---|---|---|
| Get metric | harness_get · fme_metric · params: { metric_id } |
harness get metric <id> --json |
| Get event type | harness_get · fme_event_type · params: { event_type_id } |
harness get event_type <event-name> --json |
Instructions
Phase 1: Establish scope
See scope-establishment.md. Confirm the Harness organization and project before any get operation, separately from the local application repository and intended runtime environment. Never derive Harness scope from the repo name. If application source or runtime access is unavailable, stop at guidance and label implementation/delivery unverified — CLI/MCP access does not grant application access.
Phase 2: Detect the SDK
Search existing FME track() calls first — they give the signature, key source, traffic type and wrapper in one shot; mirror them. See sdk-patterns.md for SDK detection (searching for existing track() calls or dependency manifests) and identifying whether it's a client-side or server-side SDK — the two have different track() signatures. If no flag evaluation wrapper exists yet in this app, see language-guidance.md for version-aware SDK setup, identity, readiness and fallback guidance — this skill adds a track() call to the app's existing SDK/wrapper, it does not design that wrapper (that's /instrument-feature-flag).
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 Changed · +1 lines 014c7d6c1ef9
- 9d ago First seen · 99 lines · 65 tokens per session scan C 5e116c08a529
instrument-metric is a skill published in the GitHub repository harness/harness-skills (117 stars, last pushed yesterday), licensed Apache-2.0. It adds 65 tokens to every session and 2,675 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it C with 1 finding (harvests environment variables). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-07.
Other skills, from other repositories
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
haiku
When writing a haiku for this bot, follow these conventions.
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".