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/dzearing/ghoztty-claude-plugin/process-feedbacknpx skills add dzearing/ghoztty-claude-plugin --skill process-feedbackgit clone --depth 1 https://github.com/dzearing/ghoztty-claude-pluginWrote 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/dzearing/ghoztty-claude-plugin/process-feedback)<a href="https://agentmods.dev/skills/dzearing/ghoztty-claude-plugin/process-feedback"><img src="https://agentmods.dev/badge/skills/dzearing/ghoztty-claude-plugin/process-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 | $0.00093 | $0.03027 |
| Opus 5 | $0.00046 | $0.01514 |
| Sonnet 5 | $0.00019 | $0.00605 |
| Haiku 4.5 | $0.00009 | $0.00303 |
Grade A, and why
process-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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Process Feedback
Drain the feedback queue that Ghoztty's viewer-pane feedback button produces, one report at a time, in the current worktree.
Each pass handles exactly one report and then resets context, so every report starts with a full context budget. The loop is:
claim oldest → plan → reproduce → fix (TDD) → validate → complete → /reset-context /process-feedback
Queue layout
The producer (Ghoztty) only ever writes new/. This skill owns the rest.
<repo-root>/temp/feedback/
.staging/ producer's scratch — NEVER read or claim from here
new/ unclaimed reports (producer writes here)
in-progress/ claimed; at most one, and it is yours
complete/ done and committed
blocked/ needs the user; see blocked.md inside
A report folder is self-contained:
20260721T214512Z-a3f9c2/
report.json
images/image-1.png
Reports are published atomically — do not sleep, poll, or debounce.
ViewerFeedbackReport.write builds the whole folder under
temp/feedback/.staging/<stem> and publishes it with a single rename(2) onto
the same filesystem. A folder visible in new/ is therefore complete by
construction, every image already on disk. There is no partially-populated
window to wait out and no separate "ready" directory is needed. Two cheap
guards cover everything else: ignore any entry whose name starts with ., and
require report.json to exist before claiming.
Folder names sort lexically = chronologically (yyyyMMddTHHmmssZ-<hex>), so
the oldest report is simply the first name in sorted order.
Instructions
Step 1: Locate the queue and check for an interrupted report
root=$(git rev-parse --show-toplevel) || exit 1
q="$root/temp/feedback"
mkdir -p "$q/new" "$q/in-progress" "$q/complete" "$q/blocked"
echo "QUEUE=$q"
echo "--- in-progress ---"; ls -1 "$q/in-progress" 2>/dev/null
echo "--- new ---"; ls -1 "$q/new" 2>/dev/null | grep -v '^\.' || true
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.
- 4d ago First seen · 286 lines · 93 tokens per session scan A 5531ecdd6c63
process-feedback is a skill published in the GitHub repository dzearing/ghoztty-claude-plugin (2 stars, last pushed 29d ago), licensed MIT. It adds 93 tokens to every session and 3,027 once invoked, about $0.0005 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…