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 agentmods add skills/mattgierhart/prd-driven-context-engineering/prd-v09-feedback-loop-setupnpx skills add mattgierhart/PRD-driven-context-engineering --skill prd-v09-feedback-loop-setupgit clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineeringWrote 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/mattgierhart/prd-driven-context-engineering/prd-v09-feedback-loop-setup)<a href="https://agentmods.dev/skills/mattgierhart/prd-driven-context-engineering/prd-v09-feedback-loop-setup"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v09-feedback-loop-setup.svg" alt="Measured on agentmods" 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 | $0.00094 | $0.03811 |
| Opus 5 | $0.00047 | $0.01906 |
| Sonnet 5 | $0.00019 | $0.00762 |
| Haiku 4.5 | $0.00009 | $0.00381 |
Grade A, and why
prd-v09-feedback-loop-setup 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 6d 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 — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feedback Loop Setup
Position in workflow: v0.9 Launch Metrics → v0.9 Feedback Loop Setup → v1.0 Market Adoption
Execution Mode
Default is standard. See .claude/rules/08-skill-execution-modes.md for selection logic.
| Mode | What this skill produces |
|---|---|
| quick | 1–2 channels (in-app + support); basic triage workflow |
| standard | 3–4 channels; full processing workflow + sentiment tracking + SLAs |
| deep | All channels + closed-loop tracking + voice-of-customer synthesis + escalation rules |
Consumes
This skill requires prior work from v0.9 Launch Metrics and v0.1-v0.8:
- GTM-* launch channels (from v0.9 GTM Strategy) — Active launch channels (Product Hunt, email, paid ads, etc.) become feedback sources; GTM- messaging and channels inform where feedback will arrive
- MON-* monitoring dashboards and alerts (from v0.8 Monitoring Setup) — MON- thresholds (latency, error rate, performance) define what qualifies as critical feedback; monitoring alerts can trigger deep-dive user research
- KPI-* launch targets and baselines (from v0.9 Launch Metrics) — KPI- thresholds (Day 1/7/30/90 targets) inform feedback urgency and trigger investigation when below target; baseline performance metrics (p95 latency, error rate, conversion rate) provide context for performance feedback
- CFD-* baseline entries (from v0.1-v0.4) — Baseline customer feedback hypotheses (user pain points, value propositions, competitive alternatives) become validation targets post-launch; feedback loop confirms or contradicts CFD- assumptions
- PER-* personas (from v0.4 Persona Definition) — Persona segments (PER-001 Startup Founder, PER-002 Team Lead) enable feedback categorization by user type and prioritization by persona importance
This skill assumes v0.9 Launch Metrics is live with KPI- thresholds established, GTM- channels are active, and MON- dashboards are displaying baseline metrics.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 380 lines · 94 tokens per session scan A bc8981032b20
prd-v09-feedback-loop-setup is a skill published in the GitHub repository mattgierhart/PRD-driven-context-engineering (182 stars, last pushed 5d ago), licensed MIT. It adds 94 tokens to every session and 3,811 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 skills, from other repositories
ralplan
Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution.
remember
Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs.
embedding-strategies
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.
explaining-machine-learning-models
Explain trained machine learning models through feature attribution, local explanations, and behavior summaries. Use as an explicit/manual helper once a model already exists, not for training ownership, leakage auditing, or general ML strategy selection.
nw-ddd-eventsourcing
Event Sourcing and CQRS as DDD implementation patterns — when to use, aggregate event streams, projections, snapshots, sagas, upcasting, conflict resolution.