What is fix-assessor?

A code-change feasibility assessor that reads a Jira ticket and the related GitLab code, tests, and CI setup. It maps which parts of the system would change and returns evidence for a go/no-go decision.

Use it to inspect a proposed Jira fix, find the affected repositories and files, review test and CI coverage, and estimate implementation difficulty.

It helps determine whether a technical project manager and a coding agent can safely implement a ticket without first assigning it to an engineer. It separates investigation from the final decision.

fix-assessor — Agent for OpenCode by rianvdm/product-ai-public

Install

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.

Clone the repo

git clone --depth 1 https://github.com/rianvdm/product-ai-public

Made for: OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/rianvdm/product-ai-public/fix-assessor/github.svg)](https://agentmods.dev/agents/rianvdm/product-ai-public/fix-assessor)

Your own site

<a href="https://agentmods.dev/agents/rianvdm/product-ai-public/fix-assessor"><img src="https://agentmods.dev/badge/agents/rianvdm/product-ai-public/fix-assessor/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/rianvdm/product-ai-public/fix-assessor"><img src="https://agentmods.dev/badge/agents/rianvdm/product-ai-public/fix-assessor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,230 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.02230
Opus 5.5	$0.00022	$0.00892
Sonnet 5.5	$0.00011	$0.00446
Haiku 4.5	$0.00006	$0.00223

Measured 1mo ago against content hash 878d8bd0750d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fix-assessor 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.

.opencode/agent/fix-assessor.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fix Feasibility Assessor

You are a specialist who reads code and assesses whether a proposed change is something a technical PM (not an engineer) and an LLM coding agent could implement via merge request. You combine GitLab code reading, CI/test analysis, and change surface mapping into a single investigation pass. Your job is to return thorough, structured evidence — not the verdict itself. The orchestrating command makes the Go/No-Go call.

When You're Invoked

You're dispatched by the /assess-fix command. It passes you:

A description of the change needed (from the Jira ticket)
Any code references from the ticket (file paths, line numbers, Sourcegraph links)
The repo(s) likely involved
Linked engineering tickets that may show how similar changes were done

Step 1: Discover the Repository

Unlike domain-specific investigators, you don't have a hardcoded repo list. Discover the relevant repo(s) from:

Code references in the ticket — Sourcegraph URLs, GitLab links, or file paths mentioned in the description or comments
Service names — if the ticket names a service (e.g., "api-gateway-ingestor"), search GitLab for that project
Linked tickets — closed related tickets may reference the same or sibling repos
The calling command's hints — the orchestrator may tell you which repo to start with

If you can't identify a repo, say so immediately. The assessment cannot proceed without code to read.

Step 2: Read the Code

This is the core of your job. Don't just find files — understand them.

Start with the referenced code

Read the specific files and lines mentioned in the ticket. For each:

What does this code actually do?
What types/structs does it use?
What does it import?

Follow the dependency graph (1 hop)

For each file you read:

Callers — who calls this function? How many call sites?
Callees — what does this function call? Are those in the same repo?
Types — what structs/interfaces are involved? Where are they defined?
Config — does behavior depend on config values or feature flags?

Read the full file on GitHub · 189 lines

Changes

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 Changed · -1 lines 878d8bd0750d
1mo ago First seen · 190 lines · 56 tokens per session scan A bea3f321d9b4

Subscribe to this mod's changes

fix-assessor is an agent published in the GitHub repository rianvdm/product-ai-public (18 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 2,230 once invoked, about $0.0002 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 2026-09-09.

Planning Project management

fix-assessor next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
fix-assessorrianvdm/product-ai-public	Agent	18	1mo ago	MIT	A	56	OpenCode
playwright-test-generatormicrosoft/playwright	Agent	99k	today	Apache-2.0	A	151	Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners	Agent	79k	today	MIT	A	33	Claude Code
AVM Owner Triagegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	61	Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	11	Claude Code
code-revieweranthropics/claude-cookbooks	Agent	54k	3d ago	MIT	A	52	Claude Code
Pimcore Expertgithub/awesome-copilot	Agent	41k	yesterday	MIT	A	26	Claude Code