reply-comments

A workflow for publishing already-prepared outcomes from pull-request review comments on GitHub. It treats pushing code, posting replies, and resolving discussion threads as separate actions that each need fresh confirmation.

In plain words
What is it for?
Use it after local review fixes are ready to push, explain in replies, or mark as resolved on a GitHub pull request.
Why use it?
It reduces the risk of accidentally changing a remote branch, sending a message, or closing a review discussion based on an earlier decision.

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/flurdy/agent-skills/reply-comments
Any agent
npx skills add flurdy/agent-skills --skill reply-comments
Clone the repo
git clone --depth 1 https://github.com/flurdy/agent-skills

Made for: Claude Code, Codex.

Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,046 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 $0.00038 $0.02046
Opus 5 $0.00019 $0.01023
Sonnet 5 $0.00008 $0.00409
Haiku 4.5 $0.00004 $0.00205

Measured 2d ago against content hash a510a3d98888, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

reply-comments 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 7 executable files (scripts/gh-pr-comments.sh, scripts/gh-pr-conversation-comment.sh, scripts/gh-pr-current-info.sh, …), 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/reply-comments/SKILL.md · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reply to Review Comments

Publish selected, validated feedback outcomes after /review-comments. Push, reply posting, and thread resolution are three separate visible actions, each requiring fresh current-run confirmation. Never infer remote permission from item selection, validation, a local commit, a previous run, or approval of another action.

Usage

/reply-comments                         # PR for the current branch; select eligible items
/reply-comments 123                     # backward-compatible current-repository selector
/reply-comments owner/repo#123          # repository-qualified selector
/reply-comments owner/repo#123 inline:C1 conversation:I2

Arguments identify candidates only. They are not permission to push, post, or resolve.

Instructions

1. Resolve the PR and Checkout

Accept owner/repo#number or a numeric PR. With no selector, resolve the current branch through:

~/.agents/skills/reply-comments/scripts/gh-pr-current-info.sh

Use the selected owner/repository for every GitHub call. Before offering a push, prove the current checkout's origin, branch, and HEAD correspond to that PR. Do not switch, fetch, reset, clean, merge, rebase, or overwrite work. A repository mismatch disables the push gate but does not prevent a separately validated answer/rationale from being prepared.

2. Restore Bounded Handled State

Carry forward /review-comments state when it exists. Otherwise reconstruct validation and prepared replies read-only before offering any remote action. Keep at most 500 handled actions keyed by repository/PR/identity/updateKey, recording validation, commit SHA, push result, posted reply ID, and resolution result.

On retry:

  • a recorded successful push, reply, or resolution is not repeated;
  • an inline record with a later self reply is treated as already replied;
  • an already resolved thread is recorded as complete without another mutation;
  • an uncertain or timed-out mutation result is reported as unknown — do not retry automatically;
  • if bounded state was lost, announce that idempotency continuity is unavailable and require a read-only recheck plus new confirmations. For a top-level response whose prior publication cannot be disproved from current self-comments, do not offer another post; return it for manual reconciliation.

Read the full file on GitHub · 193 lines

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. 2d ago First seen · 193 lines · 38 tokens per session scan A a510a3d98888

Subscribe to this mod's changes

reply-comments is a skill published in the GitHub repository flurdy/agent-skills (7 stars, last pushed 4d ago), licensed MIT. It adds 38 tokens to every session and 2,046 once invoked, about $0.0002 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

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