feedback

feedback is a command for Claude Code from dork-labs/dorkos. It costs 8 tokens per session (1,031 once invoked), scanned A, original, MIT.

A command for processing one piece of feedback about an implemented software change. It examines the related project code and records the decision in the feature specification’s feedback log.

In plain words
What is it for?
Use it to investigate one bug, performance issue, user-interface problem, security concern, or general improvement, then decide and record what should happen next.
Why use it?
It turns testing or usage feedback into a documented decision instead of leaving the issue unresolved or detached from the implementation.

Command for Claude Code

Part of the flow plugin — 17 skills, 37 commands, 5 agents shipped together

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/dork-labs/dorkos/feedback
Clone the repo
git clone --depth 1 https://github.com/dork-labs/dorkos

Made for: Claude Code.

Or install flow, the plugin that ships this one along with the rest of its 17 skills, 37 commands, 5 agents.

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 feedback

README.md
[![agentmods](https://agentmods.dev/badge/commands/dork-labs/dorkos/feedback.svg)](https://agentmods.dev/commands/dork-labs/dorkos/feedback)
Your own site
<a href="https://agentmods.dev/commands/dork-labs/dorkos/feedback"><img src="https://agentmods.dev/badge/commands/dork-labs/dorkos/feedback.svg" alt="Measured on agentmods" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,031 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.

ModelPer sessionOnce invoked
Fable 5 $0.00008 $0.01031
Opus 5 $0.00004 $0.00515
Sonnet 5 $0.00002 $0.00206
Haiku 4.5 $0.00001 $0.00103

Measured 3d ago against content hash fba215b8cf63, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

.claude/commands/spec/feedback.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Process Post-Implementation Feedback

Process ONE specific piece of feedback from testing/usage of an implemented spec: explore the affected code, optionally research approaches, gather decisions, and record the outcome in the spec's feedback log.

Phase 1: Validation & Setup

Extract the slug from the spec path (specs/<slug>/02-specification.md<slug>).

Verify the implementation exists: specs/<slug>/04-implementation.md must be present. If missing, stop with "Run /flow:execute first" (requires the flow plugin, dork-labs/marketplace, loaded via --plugin-dir). If specs/<slug>/03-tasks.json shows incomplete tasks, mention it as a warning — not a blocker.

Phase 2: Feedback Collection

If the user hasn't already provided the feedback, ask for ONE specific piece of feedback from testing (what's wrong or could be improved, with context/repro; one issue per session).

Categorize it: Bug/Error (fail, crash, broken), Performance (slow, timeout), UX/UI (confusing, unclear), Security (auth, permission), or General. The category steers where the exploration looks.

Phase 3: Discovery (background agents)

Always dispatch an Explore agent in the background to investigate the affected code. Its brief: read specs/<slug>/02-specification.md for component names and file paths; investigate the code areas implicated by the feedback type; and report affected components (file paths with how each relates), blast radius (direct changes / indirect impact / tests affected), immediate concerns, and recommended changes per file.

If the issue is complex enough that best-practice research would help (offer the choice for non-obvious issues), also dispatch a research-expert agent in parallel: identify the core technical challenge, compare 2-3 solution approaches with pros/cons, and report a recommended approach plus pitfalls to avoid.

Background agents notify on completion — no polling needed. Continue when their findings are in.

Phase 4: Interactive Decisions

Read the full file on GitHub · 102 lines

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. 3d ago First seen · 102 lines · 8 tokens per session scan A fba215b8cf63

Subscribe to this mod's changes

feedback is a command published in the GitHub repository dork-labs/dorkos (9 stars, last pushed today), licensed MIT. It adds 8 tokens to every session and 1,031 once invoked, about $0.0000 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.