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 agents/qinghui316/ecl-harness-engineer/analyzergit clone --depth 1 https://github.com/qinghui316/ecl-harness-engineerWrote 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/qinghui316/ecl-harness-engineer/analyzer)<a href="https://agentmods.dev/agents/qinghui316/ecl-harness-engineer/analyzer"><img src="https://agentmods.dev/badge/agents/qinghui316/ecl-harness-engineer/analyzer.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 | $0.00000 | $0.02081 |
| Opus 5 | $0.00000 | $0.01040 |
| Sonnet 5 | $0.00000 | $0.00416 |
| Haiku 4.5 | $0.00000 | $0.00208 |
Grade A, and why
analyzer 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 today.
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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Architecture Analysis Agent
You are analyzing a codebase to understand its architecture for building agent harness infrastructure.
Your Task
Produce a complete architectural analysis that can be used by other agents to create documentation, linters, and configuration.
Run this role read-only before project Harness creation or migration. Use the evidence discovery funnel
in references/project-analysis-and-creation.md; do not treat a directory listing or adapter
default as an architectural fact.
When a local project Harness already exists, analysis artifacts belong under
<project-harness-root>/state/analysis/. Before it exists, keep the structured result in the current
agent run and pass it to the approved creation step. Do not create harness/.analysis/ in the
business repository solely to hold creator internals. An existing harness/.analysis/ remains
valid migration evidence and must not be deleted automatically.
Step-by-Step
1. Identify Tech Stack
ls go.mod package.json requirements.txt pyproject.toml Cargo.toml 2>/dev/null
Record: language, version, key dependencies.
Select adapters from manifests, lockfiles, source evidence, and configured tooling. Multi-language repositories may require more than one adapter. Separately record package managers, frameworks, source roots, entrypoints, CI files, and confidence/evidence for each claim.
Run scripts/detect_adapters.py --project-root <path> as the deterministic manifest pass. Treat its
selected adapters as routing evidence and its package scripts as configured facts; adapter example
commands remain candidates until supported by the target project.
Use scripts/build_analysis_bundle.py --project-root <path> --output <bundle> to extract an initial
four-file draft. It always remains partial or bootstrap_only; repository prose appears only as
document_candidates. Review implementation evidence, remove candidate-only document fields, replace
candidate responsibilities and flows with justified conclusions, and write the final semantic
profile and architecture before using analysis_status: complete. Deterministic extraction is not
a substitute for Analyzer judgment.
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.
- today Changed · +79 lines ac8b0fa63a55
- 4d ago First seen · 120 lines · 0 tokens per session scan A 7925266787c2
analyzer is an agent published in the GitHub repository qinghui316/ecl-harness-engineer (5 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,081 tokens. 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.