run-feedback

run-feedback is a command for Claude Code from MatrixFounder/Agentic-development. It costs 0 tokens per session (250 once invoked), scanned A, original, Apache-2.0.

A command that collects and files feedback about problems encountered during the current coding session.

In plain words
What is it for?
Use it to review session friction, classify findings, and create feedback records in the project's journal.
Why use it?
It turns failed attempts, retries, and blockers into documented feedback without changing existing code or issues.

Command for Claude Code

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 commands/matrixfounder/agentic-development/run-feedback
Clone the repo
git clone --depth 1 https://github.com/MatrixFounder/Agentic-development

Made for: Claude Code.

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.

agentmods badge for run-feedback

README.md
[![agentmods](https://agentmods.dev/badge/commands/matrixfounder/agentic-development/run-feedback.svg)](https://agentmods.dev/commands/matrixfounder/agentic-development/run-feedback)
Your own site
<a href="https://agentmods.dev/commands/matrixfounder/agentic-development/run-feedback"><img src="https://agentmods.dev/badge/commands/matrixfounder/agentic-development/run-feedback.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 250 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00250
Opus 5 $0.00000 $0.00125
Sonnet 5 $0.00000 $0.00050
Haiku 4.5 $0.00000 $0.00025

Measured today against content hash bf2c9a64635c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

run-feedback 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 today.

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.

.claude/commands/run-feedback.md · 19 lines

What it actually says

Read and apply the skill defined in .agent/skills/run-feedback/SKILL.md in ad-hoc mode (§7 "Ad-hoc" — no claim/release):

  1. If the scope hint below contains mine, first run the transcript miner (python3 .agent/skills/run-feedback/scripts/run_feedback.py mine --dry-run, review the candidate yield with the user, then re-run without --dry-run if approved).
  2. Gather friction signals from the CURRENT session — failed commands, retries, exhausted gates, escalations — plus active_blockers from .agent/sessions/latest.yaml, scoped by the hint.
  3. Ask the one retro question ("Что прошло НЕ гладко?") with observed candidates pre-listed, then collecttriage → classify → file --dry-runfile, per the skill's §7 Triage protocol.
  4. Finish with a one-line report: filed IDs, dismissed count, journal path.

Apply all Global Protocols (skill-session-state). This command is non-blocking feedback collection — it never modifies existing issues or code.

Scope hint (optional): $ARGUMENTS

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.

  1. today First seen · 19 lines · 0 tokens per session scan A bf2c9a64635c

Subscribe to this mod's changes

run-feedback is a command published in the GitHub repository MatrixFounder/Agentic-development (5 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 250 tokens. 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 2026-09-03.