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 skills add 45ck/skill-harness --skill gh-review-followthroughgit clone --depth 1 https://github.com/45ck/skill-harnessWrote 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/45ck/skill-harness/gh-review-followthrough)<a href="https://agentmods.dev/skills/45ck/skill-harness/gh-review-followthrough"><img src="https://agentmods.dev/badge/skills/45ck/skill-harness/gh-review-followthrough/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/45ck/skill-harness/gh-review-followthrough"><img src="https://agentmods.dev/badge/skills/45ck/skill-harness/gh-review-followthrough.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00030 | $0.00225 |
| Opus 5.5 | $0.00012 | $0.00090 |
| Sonnet 5.5 | $0.00006 | $0.00045 |
| Haiku 4.5 | $0.00003 | $0.00022 |
Grade A, and why
gh-review-followthrough 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 1mo 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
Use this skill when the user wants comments on a GitHub pull request or issue addressed.
Process:
- verify the current branch or explicit PR maps to the right repository context
- gather open review threads or issue comments before touching code
- summarize each thread by required change, likely file scope, and any ambiguity
- have the user confirm which comments to act on when multiple threads exist
- implement only the chosen fixes, then summarize what changed and how to reply
What good looks like:
- comment handling is grouped by thread, not a random code diff
- each fix is grounded in the actual code and current reviewer request
- unresolved ambiguity is surfaced before edits, not after
- final output is ready to turn into review replies or a PR update
Avoid:
- replying to every comment with the same generic status line
- collapsing multiple unrelated review threads into one vague fix
- applying speculative changes that were not requested
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.
- 1mo ago First seen · 28 lines · 30 tokens per session scan A eb64545cf6ef
gh-review-followthrough is a skill published in the GitHub repository 45ck/skill-harness (15 stars, last pushed 4mo ago), licensed MIT. It adds 30 tokens to every session and 225 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
pull-request-feedback
Use when working through review feedback on a GitHub pull request — reading review and inline comments one by one, discussing and making changes, replying or reacting, then pushing and re-requesting review. Trigger on "review the PR feedback", "go through the comments", "address review feedback".
enable-review
Turn interactive commit reviews back on for the current herdr workspace.
hunk-launch-video
Produces Hunk videos by driving the real TUI headlessly in a PTY, compositing captioned 1080p frames in Chromium, and encoding with ffmpeg. Use for feature demos, workflow explainers, announcements, launch videos, and full-release roundups.
otto-pr-review-loop
Run Polly and OCR on a PR until all findings settle.
resolve-drive-pr
Drive an open PR through Polly/OCR, validation, and maintainer handoff.
hunk-release
Prepares, publishes, verifies, and curates Hunk releases. Use for release metadata, benchmarks, tags, publishing, release videos, backports, or recovery.