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/rianvdm/product-ai-publicWrote 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/commands/rianvdm/product-ai-public/assess-fix)<a href="https://agentmods.dev/commands/rianvdm/product-ai-public/assess-fix"><img src="https://agentmods.dev/badge/commands/rianvdm/product-ai-public/assess-fix/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/commands/rianvdm/product-ai-public/assess-fix"><img src="https://agentmods.dev/badge/commands/rianvdm/product-ai-public/assess-fix.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 | $0.00032 | $0.04647 |
| Opus 5.5 | $0.00013 | $0.01859 |
| Sonnet 5.5 | $0.00006 | $0.00929 |
| Haiku 4.5 | $0.00003 | $0.00465 |
Grade A, and why
assess-fix 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 — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Assess Fix Feasibility
You are a PM evaluating whether a Jira ticket describes a code change that a technical PM (not an engineer) could implement with the help of an LLM coding agent and submit as a merge request. Your goal is to produce a clear Go/No-Go/Maybe verdict backed by evidence, and — if the verdict is positive — a self-contained implementation brief that can be pasted into a coding agent session to produce a working MR.
Your Task
$ARGUMENTS
The argument is a Jira ticket ID (e.g., ENG-1570) or a full Jira URL. Extract the ticket ID and proceed.
Workflow
Phase 1: Understand the Ticket
Fetch the full ticket with cfi --json jira get <KEY> --comments 20 (see the cfi skill). Extract:
- Summary and description — what needs to change and why
- Code references — any file paths, line numbers, Sourcegraph URLs, or GitLab links in the description or comments
- Linked tickets — especially closed ones that show how similar changes were done
- Comments — triage notes, engineering discussion, any disagreement about approach
- The repo — identify which GitLab repository contains the code that needs to change. Look for repo names, service names, or code URLs in the ticket.
After pulling the ticket, produce a brief problem statement: what the ticket asks for, which repo is involved, and what code references exist.
Do not proceed to Phase 2 until you have identified at least one repo and have a clear understanding of what change is being requested.
Phase 2: Investigate (parallel)
Launch TWO agents in parallel. Both should return findings only — no files written.
Track 1 — @fix-assessor: Code analysis and feasibility assessment
This specialist agent reads the actual code, maps the change surface area, checks CI/test infrastructure, and scores feasibility criteria.
Task(
subagent_type="fix-assessor",
description="Assess fix feasibility for [TICKET-ID]",
prompt="I'm assessing whether [TICKET-ID] can be fixed by a technical PM with the help of an LLM coding agent.
Problem: [brief description of what needs to change]
Code references from the ticket:
[list all file paths, line numbers, Sourcegraph/GitLab URLs from Phase 1]
Repo: [gitlab path discovered in Phase 1]
Linked tickets (especially completed similar work): [list]
Please investigate following your standard workflow: discover the repo, read the referenced code, follow dependencies 1 hop out, check CI/tests/CODEOWNERS, and score all 7 feasibility criteria. Return your structured findings. Do not write any files."
)
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 · -2 lines 19082a8f4bbb
- 1mo ago Changed · +1 lines · +5 tokens per session 78b835d4e200
- 1mo ago First seen · 362 lines · 27 tokens per session scan A 3be89799b82d
assess-fix is a command published in the GitHub repository rianvdm/product-ai-public (18 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 4,647 once invoked, about $0.0001 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.
assess-fix compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| assess-fixrianvdm/product-ai-public | Command | 18 | 1mo ago | MIT | A | 32 | Claude Code, OpenCode |
| checklistgithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| clarifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 27 | Claude Code |
| specifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| analyzegithub/spec-kit | Command | 148k | yesterday | MIT | A | 26 | Claude Code |
| convergegithub/spec-kit | Command | 148k | yesterday | MIT | A | 35 | Claude Code |
| implementgithub/spec-kit | Command | 148k | yesterday | MIT | A | 14 | Claude Code |