sendback

sendback is a skill for Claude Code from escoffier-labs/skillet. It costs 51 tokens per session (1,015 once invoked), scanned A, original, MIT.

A review-feedback checking process that treats comments from people, bots, or agents as claims to verify.

In plain words
What is it for?
Use it before responding to code review feedback to determine which comments are technically valid, which need clarification, and which should be challenged.
Why use it?
It prevents blindly implementing incorrect, unclear, or misinterpreted review requests.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the skillet plugin — 39 skills, 1 hook shipped together

Good fit Use it before responding to code review feedback to determine which comments are technically valid, which need clarification, and which should be challenged.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/escoffier-labs/skillet/sendback
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.

Any agent
npx skills add escoffier-labs/skillet --skill sendback
Clone the repo
git clone --depth 1 https://github.com/escoffier-labs/skillet

Made for: Claude Code.

Or install skillet, the plugin that ships this one along with the rest of its 39 skills, 1 hook.

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 sendback

README.md
[![agentmods](https://agentmods.dev/badge/skills/escoffier-labs/skillet/sendback.svg)](https://agentmods.dev/skills/escoffier-labs/skillet/sendback)
Your own site
<a href="https://agentmods.dev/skills/escoffier-labs/skillet/sendback"><img src="https://agentmods.dev/badge/skills/escoffier-labs/skillet/sendback.svg" alt="Measured on agentmods" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,015 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00051 $0.01015
Opus 5 $0.00026 $0.00508
Sonnet 5 $0.00010 $0.00203
Haiku 4.5 $0.00005 $0.00102

Measured 8d ago against content hash 65d75a0d7393, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

sendback 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 8d 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.

skillet/skills/sendback/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

sendback

A plate comes back from the dining room. The kitchen that survives is the one that checks the plate before remaking it: sometimes the dish is wrong, sometimes the ticket was wrong, sometimes the diner ordered the wrong thing. Remaking on reflex wastes the food; arguing on reflex loses the diner. This skill is that check, applied to review feedback: verify, then implement or push back, with technical reasons either way.

Core principle: review feedback is a set of claims to verify, not orders to follow and not an audience to perform for. Reviewer seniority changes nothing; the codebase is the authority.

The pattern

For every piece of feedback, in order:

  1. Read all of it before reacting to any of it. Items relate; item 4 can change what item 1 means.
  2. Clarity gate. Any item you cannot restate concretely ("the loader issue still needs handling" - which issue? handled how?) stops the batch. Ask about the unclear items before implementing the clear ones; a guessed interpretation is a design decision nobody made, and partial understanding implements the wrong thing confidently. The one exception: an item you can show is independent of every unclear item may proceed, and the reply states that is what happened.
  3. Verify each claim against the codebase. Does the suggestion break existing behavior or a documented contract? Does a test pin the current behavior on purpose? Is there a reason the code is the way it is? Run the check (a grep, a test, a five-line repro), do not adjudicate from memory.
  4. YAGNI gate for "should also support" items. Grep for callers. Nothing uses the proposed parameter, protocol, or flexibility? The answer is "nothing calls this - skip it (YAGNI)?", not speculative API surface. The reviewer and you both work for the user; unwanted features serve neither.
  5. Then act, one item at a time, in order: blocking issues, simple fixes, complex fixes. Test each before the next; taste applies to review fixes like any other change.
  6. Reply with substance. What was done and where, what was pushed back on and the technical reason, what awaits clarification. Evidence over adjectives.

Read the full file on GitHub · 56 lines

Files

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.

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. 8d ago First seen · 56 lines · 51 tokens per session scan A 65d75a0d7393

Subscribe to this mod's changes

sendback is a skill published in the GitHub repository escoffier-labs/skillet (4 stars, last pushed 7d ago), licensed MIT. It adds 51 tokens to every session and 1,015 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.

Related

Other skills, from other repositories

production-audit

Exhaustive production-readiness audit of any codebase or product. Runs diverse-angle discovery passes until two consecutive passes find nothing new, adversarially verifies every finding against the real code, and reports one flat severity-tagged list with file:line evidence. No summary, no hedging.

apoorvjain25/production-audit · 63 tokens

craft-audit

The front door to the craft skills — a whole-project production-readiness orchestrator that drives the ten per-domain craft skills (ux, frontend, backend, db, security, infra, observability, testing, lint, ai) instead of auditing one surface at a time. It discovers the project's shape, plans an audit per surface, and…

gul-labs/craftsman-marketplace · 197 tokens

craft-backend

The Craftsman standard for building and reviewing backend code — API routes, request validation, the authentication boundary, service/business logic, error handling, route rate-limit middleware, third-party integrations, and background jobs. Use this WHENEVER the work touches the server side: adding or reviewing a…

gul-labs/craftsman-marketplace · 138 tokens

review-work

Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.

code-yeongyu/oh-my-openagent · 63 tokens

one-way-door

Flags irreversible decisions before commit. Use for data models, infra, auth boundaries, API contracts, event schemas, CI/CD.

jamditis/claude-skills-journalism · 29 tokens

critical-code-reviewer

Rigorously review code or pull requests for correctness, security, accessibility, maintainability, tests, and edge cases. Use when users request a critical code review, want a guided walkthrough of findings, need implementer-facing feedback, or want to prepare, create, or submit a GitHub pull request review.

posit-dev/skills · 67 tokens