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 skills add bjorn-ingmanson/thefroject-plugins --skill customer-feedback-orchestrationgit clone --depth 1 https://github.com/bjorn-ingmanson/thefroject-pluginsWrote 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/bjorn-ingmanson/thefroject-plugins/customer-feedback-orchestration)<a href="https://agentmods.dev/skills/bjorn-ingmanson/thefroject-plugins/customer-feedback-orchestration"><img src="https://agentmods.dev/badge/skills/bjorn-ingmanson/thefroject-plugins/customer-feedback-orchestration/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/bjorn-ingmanson/thefroject-plugins/customer-feedback-orchestration"><img src="https://agentmods.dev/badge/skills/bjorn-ingmanson/thefroject-plugins/customer-feedback-orchestration.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 | $0.00075 | $0.00954 |
| Opus 5.5 | $0.00030 | $0.00382 |
| Sonnet 5.5 | $0.00015 | $0.00191 |
| Haiku 4.5 | $0.00007 | $0.00095 |
Grade A, and why
customer-feedback-orchestration 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 2mo 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Customer Feedback Orchestration
Help the user build a continuous customer feedback program — not a one-time survey, but a system that captures, categorizes, routes, and closes the loop with customers across channels.
Gather context
Ask if not provided:
- Current state — what feedback do they collect today? (NPS, CSAT, support tickets, in-app prompts, social, sales calls, exit interviews)
- Tools — survey tool, ticketing system, CRM, analytics. Don't recommend new tools unless current ones are missing capability.
- Volume — customers, ARR, ticket volume, NPS responses per quarter.
- Goal — product input? Retention diagnosis? Story collection for marketing? Specific decision (e.g., kill or invest in feature X)?
- Owner — who runs this? (CS leader, product ops, founder, dedicated VoC role.)
The four-stage pipeline
Every mature feedback program has these stages. Map current state to each:
1. Capture (where feedback enters)
- Asked — surveys (NPS quarterly, CSAT post-ticket, post-trial offboarding).
- Volunteered — in-app feedback button, support tickets, sales call notes, churn-survey responses.
- Unprompted — social mentions, review sites, podcasts, public Slack/Discord.
The mature program covers all three. Most companies only do one (usually surveys).
2. Categorize (what it's actually about)
Build a tagging schema with 3 levels:
- Type: bug, feature request, complaint, praise, question, churn signal.
- Theme: 8-15 product/journey themes (onboarding, billing, performance, integrations, etc.).
- Severity: blocker, major, minor.
Tag every piece of feedback within 48 hours of capture. Manual at low volume; AI-assisted at high volume (use the support categorization or qualitative-analyst skill).
3. Route (who acts on what)
Each tag combination has a default owner:
- Bug + blocker = engineering on-call.
- Feature request + popular theme = product PM.
- Praise = marketing (potential testimonial / case study lead).
- Churn signal = CS leader for save attempt.
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.
- 2mo ago First seen · 84 lines · 75 tokens per session scan A 53e4f2e9243a
customer-feedback-orchestration is a skill published in the GitHub repository bjorn-ingmanson/thefroject-plugins (1 stars, last pushed 4mo ago), licensed MIT. It adds 75 tokens to every session and 954 once invoked, about $0.0003 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 2026-08-31.
customer-feedback-orchestration compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| customer-feedback-orchestrationbjorn-ingmanson/thefroject-plugins | Skill | 1 | 4mo ago | MIT | A | 75 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |