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 hashiiiii/rules-for-ai --skill hashiiiii-explain-prgit clone --depth 1 https://github.com/hashiiiii/rules-for-aiWrote 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/hashiiiii/rules-for-ai/hashiiiii-explain-pr)<a href="https://agentmods.dev/skills/hashiiiii/rules-for-ai/hashiiiii-explain-pr"><img src="https://agentmods.dev/badge/skills/hashiiiii/rules-for-ai/hashiiiii-explain-pr/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/hashiiiii/rules-for-ai/hashiiiii-explain-pr"><img src="https://agentmods.dev/badge/skills/hashiiiii/rules-for-ai/hashiiiii-explain-pr.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 | $0.00506 |
| Opus 5.5 | $0.00012 | $0.00202 |
| Sonnet 5.5 | $0.00006 | $0.00101 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
hashiiiii-explain-pr 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 yesterday.
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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explain a pull request
Explain the reviewed diff in the user's requested language and scope. Work read-only.
Gather evidence
- Read the PR title, body, commits, and complete diff. Record the reviewed base and head revisions.
- Find related issues in PR metadata and body links, then read them. A related issue is optional.
- If a source is inaccessible or the diff is incomplete, state the limit and explain the available material.
- Read surrounding code at those revisions when needed to explain behavior. Check dependency versions when choosing documentation.
Explanation
Background and purpose
Describe the background, problem, and goal in about ten lines. Use fewer lines when the evidence is sparse.
- With related issues, explain their requirements and how they relate to the PR's stated purpose.
- Without related issues, use the PR body, commit messages, and implementation before and after the change.
- Cite the sources for the stated purpose. Label inferred motivations as inferences and missing information as unknown.
Changes by meaning
Give each independent changed statement, setting, condition, or test case its own entry. Keep a single expression spanning several lines together. Split function bodies into independent statements and branches. For example, three added test cases require three entries. Cover every change within the requested scope, including tests and documentation. Group repeated equivalent edits and list their affected locations.
For each entry, use these fields:
- Location: file path, line numbers, and a short excerpt of the changed lines. Link to the reviewed revision.
- Behavior: explain what the syntax means and what changes before and after the PR.
- Purpose: explain its contribution to the PR's goal. With related issues, identify the corresponding requirement and link it.
- References: link official documentation beside the syntax or behavior it supports.
Use base-revision locations for removed code and head-revision locations for added code. Say when a unit has no established relationship to the stated purpose or leaves a requirement unmet.
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.
- yesterday First seen · 51 lines · 30 tokens per session scan A 948d77585d85
hashiiiii-explain-pr is a skill published in the GitHub repository hashiiiii/rules-for-ai (10 stars, last pushed 2d ago), licensed MIT. It adds 30 tokens to every session and 506 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 2026-10-20.
Other skills, from other repositories
issue-work-loop
Run Herdr loops for one open GitHub issue (resolve→review→fix) or an existing PR (review→lazy fixer) until CLEAN. Don't use for plain resolution without review, review-only/no-fix requests, backlog automation, or merging.
doris-repo-review
Review an Apache Doris PR from a local clone with the same multi-agent, shared-ledger convergence workflow as the CI Code Review Runner. Use when the user supplies a PR to /doris-repo-review, asks to review a Doris PR locally, or asks for the CI-style review flow. Safely align only the current worktree to the exact PR…
gh-address-comments
Address review and issue comments on the open GitHub PR for the current branch using gh CLI. Use when user says "address PR comments", "fix review feedback", "respond to PR review", or "handle PR comments". Verifies gh auth first and prompts to authenticate if not logged in. Do NOT use for creating PRs, CI debugging…
review-pr
Forensic, stage-aware pull request review. Reconstructs the commit narrative, tests architectural premises against project reality, detects over-engineering, and produces a ready-to-post review comment. Use when the user says "review PR", "review this PR", "review PR #N", "is this PR ready to merge", "review the…
azure-repos
Expert knowledge for Azure Repos development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, and integrations & coding patterns. Use when managing Git/TFVC repos, branch policies/PR checks, TFVC→Git migrations, large files, or…
review
Review in three modes — code (diff vs standards/spec), design (NOTES + tech-spec before planning), drift (implementation vs tech-spec before ship). Pick mode from Flow Conductor phase or user intent; do not mix artifact types.