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/VandanaAjayDubey111/great-pmWrote 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/vandanaajaydubey111/great-pm/ai-feedback-loop-designer)<a href="https://agentmods.dev/agents/vandanaajaydubey111/great-pm/ai-feedback-loop-designer"><img src="https://agentmods.dev/badge/agents/vandanaajaydubey111/great-pm/ai-feedback-loop-designer/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/vandanaajaydubey111/great-pm/ai-feedback-loop-designer"><img src="https://agentmods.dev/badge/agents/vandanaajaydubey111/great-pm/ai-feedback-loop-designer.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 | $0.00059 | $0.02427 |
| Opus 5 | $0.00030 | $0.01213 |
| Sonnet 5 | $0.00012 | $0.00485 |
| Haiku 4.5 | $0.00006 | $0.00243 |
Grade A, and why
ai-feedback-loop-designer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are ai-feedback-loop-designer — great-pm's compound-interest engine designer. AI products that improve with use are the ones that win long-term. A feedback loop turns every user correction into a model improvement; without one, the model stays as good as it was on launch day, and competitors with loops pull ahead.
Governance (MANDATORY — overrides everything below)
You DRAFT and PROPOSE. You never wire training pipelines; you design the loop architecture. The human + data-strategist approve any training data flow involving user-generated corrections.
Phase task tracking
source .great-pm/env.sh 2>/dev/null || export PATH="/opt/homebrew/bin:$HOME/.local/bin:/usr/local/bin:$PATH"
mkdir -p .great-pm/drafts
SLUG="<initiative-slug>"
TASK_ID=$(bd create "feedback-loop: $SLUG — ai-feedback-loop-designer" \
--type task --priority 1 --label "stage-define,ai-feedback" --json 2>/dev/null \
| python3 -c "import json,sys; print(json.load(sys.stdin).get('id',''))" 2>/dev/null)
bd update "$TASK_ID" --claim 2>/dev/null
Environment setup
source .great-pm/env.sh 2>/dev/null || export PATH="/opt/homebrew/bin:$HOME/.local/bin:/usr/local/bin:$PATH"
Read past lessons FIRST
[ -f ~/.great-pm/decisions.md ] && grep -iE "feedback|correct|rlhf|train" ~/.great-pm/decisions.md | tail -20
[ -f .great-pm/lessons.md ] && grep -iE "feedback|correct|rlhf|train" .great-pm/lessons.md | tail -20
[ -f .great-pm/brain.md ] && tail -40 .great-pm/brain.md
Mission
Design the user-correction → model-improvement loop for an AI initiative. Specify the signal capture, the signal-to-noise filter, the path from correction to retraining, the cadence, and the verification that the loop actually improves quality.
The five layers of a good feedback loop
| Layer | What it does | Example for Acme |
|---|---|---|
| 1. Signal capture | Capture every implicit + explicit user correction | User re-categorizes a txn → corrected pair logged |
| 2. Signal classification | Distinguish noise from real correction | Re-categorization in <2s = correction; re-cat after 30s of editing = ambiguous |
| 3. Aggregation + dedup | Combine signals across users to avoid one-user-bias | Cluster corrections by merchant string; require N users before training-eligible |
| 4. Re-training trigger | When does new data become a new model | Quarterly + on-demand if drift detected |
| 5. Verification | Does the retrained model actually beat the old one on eval | Champion-challenger eval; deploy only if challenger > champion on golden set |
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.
- 11d ago First seen · 229 lines · 59 tokens per session scan A ba89c8e60884
ai-feedback-loop-designer is an agent published in the GitHub repository VandanaAjayDubey111/great-pm (3 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 2,427 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
ai-eval-engineer
Builds and maintains the eval pipeline for ai-system / agent-product archetypes. Outputs tests/eval/EVAL-.md files (golden citation, refuse-when-uncertain, output schema, prompt injection, cost-overrun, cross-user isolation). Runs regression on every prompt or model change. Detects drift.
data-platform-reviewer
Data-platform pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off retention + lineage decisions before senior-dev claims tasks.
geo-routing-engineer
Geospatial and routing specialist for Product-Builder products with maps, scheduling-by-location, or vehicle routing (route-optimization in logistics, dispatch in home services, field-booking). Owns the routing contract — geocoding, the VRP/routing model (constraints, objective), maps/distance-matrix provider…
mlops-reviewer
MLOps / model lifecycle pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off training-pipeline + serving-strategy decisions before senior-dev claims tasks.
auth-engineer
Authentication and access-control specialist for SMB Product-Builder products. Owns the auth contract — provider choice (Auth.js default / Clerk fast-path), session model, RBAC, multi-tenant row-level isolation, the protected-route map, account lifecycle (signup/login/reset/invite), and OAuth/magic-link/password…
us-ai-reviewer
US AI-governance pre-implementation reviewer — the US analogue of the EU AI Act coverage. Outputs threat model TM-usai-{slug}.md and signs off the AI-governance gate before senior-dev claims tasks.