What is talksmith:feedback-cycle?

A command-line helper for managing presenter feedback in Talksmith draft and final Markdown files. It tracks feedback from its first open state through resolution and cleanup.

Use it to detect and stamp new feedback, record resolutions, mirror closed items, rescue open questions, and remove presenter-feedback sections before publishing a talk.

It removes the need to update feedback labels, copy resolved items into an audit file, and manually strip feedback from the final document. It also helps keep unresolved questions from being lost.

talksmith:feedback-cycle — Skill by veigap

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/veigap/talksmith/feedback-cycle

Any agent

npx skills add veigap/talksmith --skill feedback-cycle

Clone the repo

git clone --depth 1 https://github.com/veigap/talksmith

Made for: Claude Code, Codex.

Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,157 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.

Model	Per session	Once invoked
Fable 5	$0.00075	$0.02157
Opus 5	$0.00037	$0.01078
Sonnet 5	$0.00015	$0.00431
Haiku 4.5	$0.00007	$0.00216

Measured 2d ago against content hash e985841201d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

talksmith:feedback-cycle 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 2d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (feedback_cycle.py, find_open_notes.py, strip_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.

skills/feedback-cycle/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

talksmith:feedback-cycle — Step 5 (Review) iteration helper

Owns the mechanical bookkeeping of the Step 5 feedback loop end-to-end:

Detect unstamped presenter bullets in draft.md.
Stamp each as [open] YYYY-MM-DD — "<verbatim>".
Close each (after the Editor applies the content fix) as [closed] with a Resolution: continuation line.
Mirror every [closed] row to config/feedback-backlog.md for the cross-Talk audit trail.
Sanity-check that no [closed] bullet in draft.md is missing its mirror row.

Plus two Step-6 helpers:

Rescue still-[open] bullets from final.md into the # Open questions section (so they survive the strip pass) — find_open_notes.py / rescue-open.
Strip every Presenter feedback field out of final.md at Step 6 (d) — strip_feedback.py — removing both authored forms (H3 / paragraph) and guaranteeing a blank line before every --- slide boundary so a strip can never fuse two slides into a setext-H2 heading. Deterministic; the Editor never hand-strips these blocks.
```
python3 ${CLAUDE_PLUGIN_ROOT}/skills/feedback-cycle/strip_feedback.py talks/<Talk>/final.md [--dry-run]
```

The LLM Editor calls these as CLI subcommands and only authors three things per bullet: the per-slide content fix, the one-sentence resolution, and the tag list. Every line edit on draft.md and every row appended to feedback-backlog.md goes through this skill — the Editor does not read draft.md end-to-end during a normal Review round.

When to use

Every Step 5 (Review) round. Start with find-open to get the precise bullet list, then stamp / apply fix / close / mirror-row per bullet, then find-closed-unmirrored as a sanity check.
Step 6 (c) Polish. Run rescue-open once against final.md to copy any surviving [open] bullets into # Open questions before Step 6 (d) strips Presenter-feedback fields.
Spot-check after applying feedback — re-run find-open to confirm nothing was missed.

Read the full file on GitHub · 132 lines

Files

What ships with it

3 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.

2d ago First seen · 132 lines · 75 tokens per session scan A e985841201d9

Subscribe to this mod's changes

talksmith:feedback-cycle is a skill published in the GitHub repository veigap/talksmith (10 stars, last pushed 4d ago), licensed MIT. It adds 75 tokens to every session and 2,157 once invoked, about $0.0004 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.

Writing and docs

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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.

obra/superpowers · 37 tokens

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.

microsoft/vscode · 62 tokens

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.

microsoft/vscode · 51 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens