Borrowing it
Nothing to install: this file belongs to Rul1an/assay. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Rul1an/assay/main/.agents/skills/assay-golden-path/SKILL.mdgit clone --depth 1 https://github.com/Rul1an/assayWrote 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/rul1an/assay/assay-golden-path)<a href="https://agentmods.dev/skills/rul1an/assay/assay-golden-path"><img src="https://agentmods.dev/badge/skills/rul1an/assay/assay-golden-path/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/rul1an/assay/assay-golden-path"><img src="https://agentmods.dev/badge/skills/rul1an/assay/assay-golden-path.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 | $0.00056 | $0.02038 |
| Opus 5 | $0.00028 | $0.01019 |
| Sonnet 5 | $0.00011 | $0.00408 |
| Haiku 4.5 | $0.00006 | $0.00204 |
Grade A, and why
assay-golden-path 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 7d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Assay Golden Path
Drive the nine steps below in order. Read stdout and the process exit code separately; a policy denial can be a successful JSON-RPC exchange rather than a process failure.
docs/generated/agent-golden-path.json is the authoritative machine contract.
Read it when exact argv, fields, or per-outcome metadata are needed. Edit and
run scripts/docs/generate-agent-golden-path.py instead of editing this file.
When a step has no working_directory, run it from the invocation cwd.
A present working_directory is a POSIX path relative to the source repository.
Replace <python> with python3 on Unix-like hosts or python on Windows.
Empty stdout in a gap row is an observed limitation, not permission for a caller to infer success from missing evidence. Do not replace a linked gap with an inferred clean result.
Codex and Claude Code are the project-skill hosts exercised here. Cursor's skill documentation (https://cursor.com/docs/skills), accessed on 2026-08-09, describes .agents/skills as a project-level location and .claude/skills as a compatibility location. This repository does not exercise Cursor runtime discovery.
Journey
1. Install check
Run: assay version
Exit: Success 0.
Stdout: One MAJOR.MINOR.PATCH line.
On failure: A missing or unstartable binary is a host spawn failure: no Assay process runs, so Assay produces no stdout or exit code.
2. Preflight
Run: assay doctor --format json --config <config>
Exit: Success 0; no config examined 0; config examined, error-severity diagnostic 2; absent explicit config 2; invalid explicit config 2.
Stdout: Parses as assay.doctor_report.v0. Every report carries config_check.status, one of checked, skipped or failed. Exit 0 on its own does not mean a config was examined: read config_check.status to tell a clean config from no config. A config that was examined and carries an error-severity data_diagnostics[] entry exits 2, the class decide_exit gives that diagnostic for assay validate and assay run too; the text channel returns the same class for the same tree. A config failure remains JSON and carries the top-level reason_code and next_step alongside config_error.code.
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.
- 7d ago Changed 6676d9a28ec1
- 12d ago First seen · 127 lines · 56 tokens per session scan A 0b30e1d80946
assay-golden-path is a skill published in the GitHub repository Rul1an/assay (10 stars, last pushed today), licensed MIT. It adds 56 tokens to every session and 2,038 once invoked, about $0.0003 per session on Opus 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 2026-08-31.
Other skills, from other repositories
qa
QA test a live website with Axon discovery/content evidence plus browser automation when interaction is required. Use when the user wants exploratory QA, form testing, navigation/link checks, responsive checks, performance observations, bug reports, or a pre-launch quality review.
troubleshoot
Troubleshoot cortex connection failures, missing logs, unhealthy containers, restart loops, or vague "logs aren't working" reports.
chrome-devtools-cli
Use this skill to write shell scripts or run shell commands to automate tasks in the browser or otherwise use Chrome DevTools via CLI.
a11y-debugging
Uses Chrome DevTools MCP for accessibility (a11y) debugging and auditing based on web.dev guidelines. Use when testing semantic HTML, ARIA labels, focus states, keyboard navigation, tap targets, and color contrast.
chrome-devtools
Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to --slim mode (MCP configuration).
n8n-error-handling
Wire n8n error handling so failures are loud, structured, and recoverable. Use when building any webhook/API workflow, a scheduled or unattended workflow, or any path where a silent failure would drop user-visible work — and whenever the user mentions error handling, onError, continueErrorOutput, error…