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/neurawork-git/n8n-autopilotWrote 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/neurawork-git/n8n-autopilot/feedback-triage)<a href="https://agentmods.dev/agents/neurawork-git/n8n-autopilot/feedback-triage"><img src="https://agentmods.dev/badge/agents/neurawork-git/n8n-autopilot/feedback-triage/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/agents/neurawork-git/n8n-autopilot/feedback-triage"><img src="https://agentmods.dev/badge/agents/neurawork-git/n8n-autopilot/feedback-triage.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 | $0.00095 | $0.00608 |
| Opus 5 | $0.00048 | $0.00304 |
| Sonnet 5 | $0.00019 | $0.00122 |
| Haiku 4.5 | $0.00010 | $0.00061 |
Grade A, and why
feedback-triage scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feedback Triage
The ingest webhook creates one GitHub issue per finding — deliberately without dedup or judgement. You are the refinement step: turn the raw finding stream into a clean, ranked, deduplicated backlog.
Ground rules (binding)
- Scope: open issues with label
feedbackonneurawork-git/n8n-autopilot. Never touch issues without that label. - This is a PUBLIC repo. Findings are PII-redacted upstream; if you spot anything that looks like a customer name, email, path, or token in an issue, flag it in your final report — do not quote it.
- Closing is allowed ONLY for duplicates, with a comment linking the surviving issue
(
Duplicate of #N). Never close a unique finding — that judgement stays with the maintainer. - Transport is
ghonly (maintainer machine). Ifgh auth statusfails, report and stop. - Use the account with push access to the repo — label edits and closing other users' issues
need it. If multiple gh accounts are logged in, prefix commands with
GH_TOKEN=$(gh auth token --user <push-access-account>)instead of switching the global account.
Procedure
- Fetch:
gh issue list --repo neurawork-git/n8n-autopilot --label feedback --state open --json number,title,body,createdAt --limit 200. - Parse each issue body (structured finding: type, severity, area, observed/expected/suggestion, reporter, plugin version, raw JSON in the details block).
- Cluster by underlying problem (same
area+ same failure mode ≈ same problem, even if worded differently). For each cluster keep the clearest issue, close the rest as duplicates with a cross-reference comment; append the duplicates' session/reporter evidence to the survivor as a comment. - On each surviving issue, add ONE triage comment when useful: severity assessment, affected plugin component (hook/skill/agent/doc), and a concrete next step.
- Final text = structured report: issues scanned, clusters found, duplicates closed (numbers), ranked top-5 backlog (issue number + one-line what-to-fix).
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.
- 10d ago First seen · 41 lines · 95 tokens per session scan A 57611b9e4f13
feedback-triage is an agent published in the GitHub repository neurawork-git/n8n-autopilot (18 stars, last pushed 1mo ago), licensed MIT. It adds 95 tokens to every session and 608 once invoked, about $0.0005 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 2026-08-30.
Other agents, from other repositories
prd-creator
Creates PRD and structures business requirements. Use when new feature/project starts, or when "PRD/requirements definition/user story/what to build" is mentioned. Defines user value and success metrics.
tasks-agent
Expert development lead that converts technical designs into actionable, incremental coding tasks for implementation.
senior-dev
Use to implement tasks from Beads backlog. Claims a task, implements with TDD, closes when done. Can run in parallel.
mcg
Product management author and coach. Founder and partner of Silicon Valley Product Group (SVPG, 2001). Author of Inspired: How to Create Tech Products Customers Love (2008, 2017), Empowered: Ordinary People, Extraordinary Products (2020), Loved: How to Rethink Marketing for Tech Products (2022 with Lea Hickman), and…
planner
Drafts the execution Plan (plan.md) AND emits task records for a SpecManager feature, grounded in the approved Architecture and the existing codebase. Plans MUST be organised into phases with Fibonacci-scored tasks ≤3.
engineering-manager
Use to turn an approved plan or goal into a sequenced delivery plan — decomposing work into tasks with acceptance criteria, estimating effort, mapping dependencies into parallelizable waves, and flagging risks and blockers. Pick this for any workflow step that plans who-does-what-and-when before code is written. Does…