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 sleeyax/promptfiles --skill address-reviewgit clone --depth 1 https://github.com/sleeyax/promptfilesWrote 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/sleeyax/promptfiles/address-review)<a href="https://agentmods.dev/skills/sleeyax/promptfiles/address-review"><img src="https://agentmods.dev/badge/skills/sleeyax/promptfiles/address-review/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/sleeyax/promptfiles/address-review"><img src="https://agentmods.dev/badge/skills/sleeyax/promptfiles/address-review.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 | $0.00061 | $0.01952 |
| Opus 5 | $0.00030 | $0.00976 |
| Sonnet 5 | $0.00012 | $0.00390 |
| Haiku 4.5 | $0.00006 | $0.00195 |
Grade A, and why
address-review 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.
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.
Address Review Comments
PR/MR (optional): $ARGUMENTS
Pull the review feedback left on a pull request or merge request, decide what actually needs changing, and land each addressed comment as its own commit.
$ARGUMENTS is optional — with no argument, the target is the open PR/MR for the current branch. Example invocations: /address-review, /address-review 42, /address-review <mr-url>.
Hard rules
- Every gate — target confirmation, dirty-tree, which comments to address, thread replies — is a real stop: ask, then wait for the answer. Use the
AskUserQuestiontool when it's available in the session; where it isn't (e.g. Codex), ask in plain text with the same numbered options and stop until the user replies. Never assume an answer. Committing is not one of these gates — thegit-commitskill commits on its own. - One commit per comment. Group only when several comments demand the same edit; say so in the report when you do.
- Never write back to GitHub/GitLab (pushes, replies, resolves) unless the user explicitly opts in at step 8. The default is local-only: commits stay on the machine and the user pushes manually.
- Pushing is coupled to replying. Push only as part of a step 8 reply option, and only before posting — never as a standalone step, and never force-push.
- Don't blindly obey a comment. A reviewer can be wrong or working from stale context — flag disagreements instead of implementing them.
- Don't dump the full diff into a prompt or a file. Read the files the comments point at.
Workflow
1. Resolve the target
Determine the provider from git remote -v:
- Contains
github.com→ GitHub - Contains
gitlab.comor a self-hosted GitLab host → GitLab - Otherwise ask the user which provider to use.
Then resolve which PR/MR:
$ARGUMENTSis empty (the common case) → detect the current branch withgit rev-parse --abbrev-ref HEADand look up the open PR/MR whose source branch is that branch:- GitHub:
gh pr view --json number,title,url,state(resolves from the current branch), orgh pr list --head <branch> --json number,title,url,stateif that fails. - GitLab:
glab mr view, orglab mr list --source-branch <branch>. - No match → don't guess. Tell the user the branch has no open PR/MR and ask for a URL or number.
- Several matches → ask, listing them (number + title) so the user picks.
- On the default branch with no argument → stop and ask; there's nothing sensible to infer.
- GitHub:
$ARGUMENTSis a URL → parse host, project path, and number from it.$ARGUMENTSis a bare number (strip a leading#) → that PR/MR in the current repo.
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 · 132 lines · 61 tokens per session scan A abcbe306a05b
address-review is a skill published in the GitHub repository sleeyax/promptfiles (2 stars, last pushed 11d ago), licensed MIT. It adds 61 tokens to every session and 1,952 once invoked, about $0.0003 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
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
github-pr-workflow
Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
review-delta
Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.
github-contributor
End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain — discovery, CONTRIBUTING compliance, PR-size check, minimal-diff implementation, PR description with AI-assisted disclosure, conflict resolution, and post-submission maintainer interaction. Use whenever creating…
pr-pending-feedback
Evaluate pending (unsubmitted) review comments on the current branch's PR and, after user confirmation, address each in a separate sub-agent and separate commit.