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 skills/harness/harness-ai/debug-pipelinenpx skills add harness/harness-ai --skill debug-pipelinegit 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/skills/harness/harness-ai/debug-pipeline)<a href="https://agentmods.dev/skills/harness/harness-ai/debug-pipeline"><img src="https://agentmods.dev/badge/skills/harness/harness-ai/debug-pipeline.svg" alt="Measured on agentmods" 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 | $0.00121 | $0.01500 |
| Opus 5 | $0.00060 | $0.00750 |
| Sonnet 5 | $0.00024 | $0.00300 |
| Haiku 4.5 | $0.00012 | $0.00150 |
Grade A, and why
debug-pipeline 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 5d 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.
This is a copy
100% identical to debug-pipeline — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug Pipeline
Diagnose pipeline executions and suggest fixes via MCP.
Instructions
Step 1: Diagnose Execution (Preferred)
Use the dedicated diagnosis tool. It accepts an execution_id, pipeline_id (auto-fetches latest execution), or a Harness URL:
Call MCP tool: harness_diagnose
Parameters:
pipeline_id: "<pipeline_identifier>" # or execution_id or url
org_id: "<organization>"
project_id: "<project>"
This returns a structured report with stage/step breakdown, timing, bottlenecks, and failure details in one call. It also automatically follows chained (child) pipeline failures.
Step 1b: Full Diagnostic Mode
For deeper analysis, request logs and pipeline YAML:
Call MCP tool: harness_diagnose
Parameters:
execution_id: "<execution_id>"
org_id: "<organization>"
project_id: "<project>"
summary: false # raw diagnostic payload
include_yaml: true # include pipeline definition
include_logs: true # include failed step logs
log_snippet_lines: 120 # tail N lines per step (0 = unlimited)
max_failed_steps: 5 # cap number of steps to fetch logs for
Diagnose Parameters
| Parameter | Default | Description |
|---|---|---|
execution_id |
-- | Specific execution to analyze |
pipeline_id |
-- | Fetch latest execution for this pipeline |
url |
-- | Harness UI URL (auto-extracts IDs) |
summary |
true | Structured report (true) or raw payload (false) |
include_yaml |
false (summary) / true (raw) | Include pipeline YAML definition |
include_logs |
false (summary) / true (raw) | Include failed step logs |
log_snippet_lines |
120 | Max log lines per step (tail). 0 = unlimited |
max_failed_steps |
5 | Max steps to fetch logs for. 0 = unlimited |
Step 2: Project Health Overview
Check overall project health for context:
Call MCP tool: harness_status
Parameters:
org_id: "<organization>"
project_id: "<project>"
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.
- 5d ago First seen · 209 lines · 121 tokens per session scan A 9b631e5644f4
debug-pipeline is a skill published in the GitHub repository harness/harness-ai (19 stars, last pushed 14d ago), licensed Apache-2.0. It adds 121 tokens to every session and 1,500 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to debug-pipeline, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…