harness-feedback

harness-feedback is a skill for Claude Code, Codex from CATWILLgh/MAINFRAME. It costs 55 tokens per session (351 once invoked), scanned A, original, MIT.

A reporting tool for recording concrete problems caused by the MAINFRAME development harness, such as false alarms, permission friction, unclear instructions, or missing capabilities.

In plain words
What is it for?
Use it after resolving a reproducible harness issue to file one report with the trigger, expected and actual behavior, type, severity, and an optional improvement.
Why use it?
It separates problems in the development harness from defects in the project being built and preserves a structured report for later review.

Skill for Claude CodeCodex

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 skills/catwillgh/mainframe/harness-feedback
Any agent
npx skills add CATWILLgh/MAINFRAME --skill harness-feedback
Clone the repo
git clone --depth 1 https://github.com/CATWILLgh/MAINFRAME

Made for: Claude Code, Codex.

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 harness-feedback

README.md
[![agentmods](https://agentmods.dev/badge/skills/catwillgh/mainframe/harness-feedback.svg)](https://agentmods.dev/skills/catwillgh/mainframe/harness-feedback)
Your own site
<a href="https://agentmods.dev/skills/catwillgh/mainframe/harness-feedback"><img src="https://agentmods.dev/badge/skills/catwillgh/mainframe/harness-feedback.svg" alt="Measured on agentmods" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 351 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 $0.00055 $0.00351
Opus 5 $0.00028 $0.00176
Sonnet 5 $0.00011 $0.00070
Haiku 4.5 $0.00006 $0.00035

Measured 3d ago against content hash e44e1b0cb3d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

harness-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.

The scan reads SKILL.md. This mod also ships 1 executable file (feedback.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

adapters/claude-code/dev/skills/harness-feedback/SKILL.md · 38 lines

What it actually says

Harness feedback

Record what Claude Code encountered, not a general opinion. Reports go to the Claude adapter's private development queue and are candidates for later review. Filing never waives a gate or replaces fixing the active task. Optional Spark analysis may start after the durable write; it never changes the command result.

Run feedback.py from this skill directory with the report body on stdin:

python3 "<this skill's base dir>/feedback.py" \
  --artifact "<exact hook, rule, skill, or agent>" \
  --type <false-positive|friction|unclear-instruction|missing-capability|other> \
  --severity <low|medium|high> \
  --title "<one line>" <<'EOF'
## Trigger
<exact command, tool call, or file and line>

## Expected vs actual
<what should have happened and what happened>

## Suggestion
<optional bounded improvement>
EOF

Do not include secrets, whole files, praise, or project-code defects. If a quoted command would itself trigger a permission rule, write the body with the file-writing tool and redirect that file into the receiver.

Files

What ships with it

1 file 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. 3d ago First seen · 38 lines · 55 tokens per session scan A e44e1b0cb3d1

Subscribe to this mod's changes

harness-feedback is a skill published in the GitHub repository CATWILLgh/MAINFRAME (2 stars, last pushed 13d ago), licensed MIT. It adds 55 tokens to every session and 351 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

cc-hooks

Multi-agent hook system: author hooks once as rulesync-canonical hooks.json (HookDefinitionSchema), deploy via superskill install / superskill hook emit to Claude Code, Codex, OpenCode, Pi (pi-hooks), and Gemini CLI. Covers command, prompt, and http hooks, cross-platform event mapping, and safety invariants.

gobing-ai/superskill · 71 tokens

built-for-shopify-standards

Prepare a Shopify app for Built for Shopify status. Covers current quality criteria, performance, accessibility, Shopify admin integration, compliance webhooks, observability, support, application readiness, and ongoing eligibility.

khadinakbarlabs/shopify-app-builder · 47 tokens

dev-troubleshooting

Use when a Shopify dev workflow is failing — shopify app dev cryptic errors, Cloudflare tunnel not starting, App Bridge v3→v4 migration 'No AppBridge context provided', GraphQL 200 OK with throttle errors, webhook 401, double-subscribed webhooks, app proxy 404, REST 302 loops, Rust function wasm-validator errors…

khadinakbarlabs/shopify-app-builder · 175 tokens

merchant-pain-prevention

Use when designing, building, reviewing, or shipping a Shopify app to avoid the patterns that get merchants angry (1-2 star reviews, uninstalls, churn). Covers theme injection / leftover code on uninstall, surprise billing, fake urgency, slow scripts, cancel friction, scope creep, bot-only support, broken on platform…

khadinakbarlabs/shopify-app-builder · 162 tokens

app-pricing-strategy

Use when designing Shopify app pricing, choosing a pricing model (flat tiered / usage-based / freemium / hybrid), setting trial length (7/14/30 days), structuring 3-4 tier plans, sizing capped usage, raising prices on existing customers, or writing pricing copy for the App Store listing. Triggers: 'shopify app…

khadinakbarlabs/shopify-app-builder · 146 tokens

ux-modern-app-feel

Use when you want a Shopify embedded app to feel modern, fast, and opinionated like Linear, Notion, Vercel, or Cron — speed-first, keyboard-first, calm UI, opinionated defaults, no-config success path. Covers keyboard shortcuts inside App Bridge, command palette patterns, micro-interactions Polaris allows, density vs…

khadinakbarlabs/shopify-app-builder · 162 tokens