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 Starfie1d1272/dsh-github-skills --skill gh-address-commentsgit clone --depth 1 https://github.com/Starfie1d1272/dsh-github-skillsWrote 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/starfie1d1272/dsh-github-skills/gh-address-comments)<a href="https://agentmods.dev/skills/starfie1d1272/dsh-github-skills/gh-address-comments"><img src="https://agentmods.dev/badge/skills/starfie1d1272/dsh-github-skills/gh-address-comments/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/starfie1d1272/dsh-github-skills/gh-address-comments"><img src="https://agentmods.dev/badge/skills/starfie1d1272/dsh-github-skills/gh-address-comments.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 | $0.00044 | $0.00454 |
| Opus 5 | $0.00022 | $0.00227 |
| Sonnet 5 | $0.00009 | $0.00091 |
| Haiku 4.5 | $0.00004 | $0.00045 |
Grade A, and why
gh-address-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 10d 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
GitHub PR Review Feedback
Work through requested changes on a GitHub pull request using thread-aware review state.
Evidence
- Flat comments are not thread-aware review state (resolved/outdated/ inline-anchor semantics). Never collapse threads into flat comments.
- Use a visible structured-metadata capability when suitable; use a
thread-aware capability only if it genuinely preserves resolved/outdated/
inline-anchor semantics; otherwise use
scripts/fetch-review-threads.mjs. - Keep conversation comments, reviews, and review threads distinct.
- Incomplete or truncated evidence (
commentsTruncated) must be reported, never presented as a complete view.
Workflow
- Resolve the PR (given repo + number/URL, or current branch via local git context; ask if still ambiguous).
- Fetch the complete review context (see Evidence), then classify each thread: actionable, informational, already resolved/outdated, or ambiguous.
- Cluster actionable threads by file or behavior area; keep each change traceable to the thread or cluster it addresses.
- Decide intent. Analysis-only ("look at the review") gets analysis only. Address/fix intent ("address the review") authorizes local edits for unresolved actionable threads without mechanically re-asking.
- Surface conflicts, ambiguity, or regression risk before editing.
- Verify with the most relevant local checks for the touched area; never claim verification you did not run.
- Report addressed threads (file/line), intentionally unaddressed items and why, checks run, and remaining risk.
Remote write boundary
Local edits are not GitHub writes. Reply, resolve threads, submit a review,
push, or update the PR only on explicit user request or the host approval
boundary. If gh auth is missing or fails, report the blocker instead of
guessing.
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.
- 10d ago First seen · 47 lines · 44 tokens per session scan A 20ccc961474a
gh-address-comments is a skill published in the GitHub repository Starfie1d1272/dsh-github-skills (6 stars, last pushed 21d ago), licensed Apache-2.0. It adds 44 tokens to every session and 454 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.
Other skills, from other repositories
github
Use the connected iPolloWork GitHub service to inspect repositories, pull requests, issues, reviews, and Actions, then route focused work to the review, CI, or publish skill.
github-publish-changes
Publish intentional local changes by confirming scope, creating a branch when needed, staging selected files, committing, pushing, and creating a Draft Pull Request through the connected GitHub service.
github-review-follow-up
Inspect unresolved GitHub pull request review threads, group actionable feedback, implement selected fixes locally, and only reply or resolve threads after explicit user intent.
code-review
A review of changes made after a specified commit, branch, tag, or merge point. It checks both the project's coding standards and whether the changes implement the original issue or specification.
gentle-ai-collab-perfect
Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the…
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.