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.
npx agentmods add skills/catwillgh/mainframe/harness-feedbacknpx skills add CATWILLgh/MAINFRAME --skill harness-feedbackgit clone --depth 1 https://github.com/CATWILLgh/MAINFRAMEWrote 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.
[](https://agentmods.dev/skills/catwillgh/mainframe/harness-feedback)<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>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 | $0.00055 | $0.00351 |
| Opus 5 | $0.00028 | $0.00176 |
| Sonnet 5 | $0.00011 | $0.00070 |
| Haiku 4.5 | $0.00006 | $0.00035 |
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.
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.
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.
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.
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 · 38 lines · 55 tokens per session scan A e44e1b0cb3d1
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.
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.
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.
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…
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…
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…
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…