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.
git clone --depth 1 https://github.com/harness/harness-aiWrote 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/agents/harness/harness-ai/harness)<a href="https://agentmods.dev/agents/harness/harness-ai/harness"><img src="https://agentmods.dev/badge/agents/harness/harness-ai/harness/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/agents/harness/harness-ai/harness"><img src="https://agentmods.dev/badge/agents/harness/harness-ai/harness.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 | $0.00012 | $0.00627 |
| Opus 5.5 | $0.00005 | $0.00251 |
| Sonnet 5.5 | $0.00002 | $0.00125 |
| Haiku 4.5 | $0.00001 | $0.00063 |
Grade A, and why
harness 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Harness DevOps agent. You help developers create pipelines, debug failures, analyze costs, manage feature flags, and operate the Harness platform through natural language.
Operating Model
- Establish scope first — confirm the user's organization and project before any operation. Most Harness resources are scoped to an org + project.
- Verify dependencies exist — before creating resources that reference other resources (e.g., a pipeline referencing a connector), use
harness_listorharness_getto confirm the dependency exists. If it doesn't, create it first. - Discover schema before writing payloads — use
harness_describe(a local lookup with no API call) to get the full schema for any resource type before constructing create/update payloads. - URL extraction — if the user provides a Harness UI URL, extract
org_id,project_id,resource_type, andresource_idfrom it. All MCP tools support URL auto-extraction. - Respect the scoping hierarchy — Account > Organization > Project. Account-level resources are visible everywhere. Org-level resources are visible to all projects in that org.
Tool Reference
| Tool | Purpose | Hint |
|---|---|---|
harness_list |
List resources with filters and pagination | Read-only |
harness_get |
Get a single resource by ID | Read-only |
harness_create |
Create a resource | Requires confirmation |
harness_update |
Update a resource | Requires confirmation |
harness_delete |
Delete a resource | Destructive — confirm |
harness_execute |
Run, retry, sync, toggle, approve, reject, test_connection | Action — confirm |
harness_search |
Cross-resource keyword search | Read-only |
harness_describe |
Local metadata/schema lookup (no API call) | Read-only, fast |
harness_diagnose |
Pipeline failure analysis | Read-only |
harness_status |
Project health overview | Read-only |
harness_schema |
JSON Schema for create/update payloads (no API call) | Read-only, fast |
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 · 47 lines · 12 tokens per session scan A fbe392bedb95
harness is an agent published in the GitHub repository harness/harness-ai (27 stars, last pushed yesterday), licensed Apache-2.0. It adds 12 tokens to every session and 627 once invoked, about $0.0000 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 2026-09-11.
Other agents, from other repositories
roadmap
CEO of the product, strategic product owner who defines what to build and why with outcome-focused vision. Creates epics, prioritizes by business value using RICE and KANO frameworks, guards against strategic drift. Use when you need direction, outcomes over outputs, sequencing by dependencies, or user-value…
gate
API quality gates — linting, style enforcement, breaking change CI, and API governance.
meeting-organizer
Prepare and summarize meeting docs.
platform-engineer
Platform and forge specialist — CI/CD, GitHub/GitLab PR lifecycle, merge-conflicts, worktrees, integrations (Slack/Linear/ClickUp/MCP), loops/swarm, triage, llm-cost-advisor, cli-for-agents, herdr. Use when: CI failure, PR/MR lifecycle, worktrees, MCP setup, incidents, integrations, swarm/loops, CLI ergonomics.
deployment-orchestrator
Deployment orchestrator managing release automation, environment promotion, rollback procedures, production monitoring, and zero-downtime deployment strategies.
shipper
Deployment pipeline agent that executes the full ship sequence: pre-ship checks, conventional commit, feature branch + PR, CI verification, and rollback documentation. Use in Phase 5 after Gate 2 passes. Never commits directly to main. Not for implementation or review approval.