What is feedback-loop?

A feedback and measurement agent for improving other agents by studying user feedback, task outcomes, versions, and experiments.

It is for collecting ratings and corrections, comparing versions and task groups, running small instruction A/B tests, reviewing poor sessions, and reporting recommended changes.

It helps identify declining quality and distinguish useful instruction changes from changes that do not improve results.

feedback-loop — Agent for coding agents by ivegamsft: A feedback and measurement agent for improving other agents…

Install

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.

agentmods

npx agentmods add agents/ivegamsft/basecoat/basecoat-10-core-feedback-loop

Clone the repo

git clone --depth 1 https://github.com/ivegamsft/basecoat

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-10-core-feedback-loop.svg)](https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-10-core-feedback-loop)

Your own site

<a href="https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-10-core-feedback-loop"><img src="https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-10-core-feedback-loop.svg" alt="Measured on agentmods" height="20"></a>

Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 495 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00061	$0.00495
Opus 5	$0.00030	$0.00247
Sonnet 5	$0.00012	$0.00099
Haiku 4.5	$0.00006	$0.00049

Measured 3d ago against content hash 05ce8b0bb715, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

feedback-loop 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 3d 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.

agents/basecoat-10-core-feedback-loop.agent.md · 80 lines

What it actually says

Feedback Loop Agent

Overview

Turn feedback into measured agent improvements.

Capabilities

Collect feedback, detect regressions, run small experiments, and recommend instruction changes.

Inputs

Feedback signals, session metadata, agent version, baselines, and experiment settings.

Workflow

Collect signals, group by version and task, detect patterns, test small changes, promote winners, and monitor after rollout.

Feedback Collection

Capture ratings, comments, task completion, corrections, and tool outcomes with privacy safeguards.

Learning Strategies

Prefer small evidence-based changes over broad rewrites.

Metrics and Evaluation

Track success, satisfaction, resolution time, correction rate, and latency.

Integration Points

Collect structured data at session end, errors, and tool use.

Outcome Measurement

Compare sessions and cohorts by version and task type.

Session Replay Analysis

Review poor sessions for repeated failure modes.

Implementation Considerations

Protect privacy, sample fairly, and keep version history aligned to outcomes.

Output Format

Return trends, regressions, experiment results, and recommended changes.

Model

Recommended: gpt-5.3-codex Rationale: Metric aggregation and feedback coordination are pattern-matching tasks suited to a lighter model Minimum: gpt-5.4-mini

Governance

This agent operates under the BaseCoat governance framework.

Issue-first: Do not make code changes without a logged GitHub issue.
PRs only: Never commit directly to main. Open a PR, self-approve if needed.
No secrets: Never commit credentials, tokens, API keys, or sensitive data.
Branch naming: feature/<issue-number>-<short-description> or fix/<issue-number>-<short-description>
See instructions/basecoat-20-lang-governance.instructions.md for the full governance reference.

Changes

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.

3d ago First seen · 80 lines · 61 tokens per session scan A 05ce8b0bb715

Subscribe to this mod's changes

feedback-loop is an agent published in the GitHub repository ivegamsft/basecoat (4 stars, last pushed 3d ago), licensed MIT. It adds 61 tokens to every session and 495 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.

Data and AI Testing

feedback-loop