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 adrielp/ai-engineering-harness --skill pr-description-generatorgit clone --depth 1 https://github.com/adrielp/ai-engineering-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/adrielp/ai-engineering-harness/pr-description-generator)<a href="https://agentmods.dev/skills/adrielp/ai-engineering-harness/pr-description-generator"><img src="https://agentmods.dev/badge/skills/adrielp/ai-engineering-harness/pr-description-generator.svg" alt="Measured on agentmods" 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 | $0.00037 | $0.01250 |
| Opus 5 | $0.00018 | $0.00625 |
| Sonnet 5 | $0.00007 | $0.00250 |
| Haiku 4.5 | $0.00004 | $0.00125 |
Grade A, and why
pr-description-generator 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 8d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- pr_description_generator — 89% identical, 8 lines differ
How it starts
The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Description Generator
When to Use This Skill
Activate this skill when the user:
- Asks to "create a PR description" or "describe this PR"
- Says "generate PR description" or "write PR description"
- Mentions "pull request" in context of documenting changes
- Asks to "update PR description" for an existing PR
Core Process
Step 1: Locate the PR Description Template
Check for template in standard locations:
# Project-specific template
test -f thoughts/shared/pr_description.md && echo "Found"
# Alternative locations
test -f .github/pull_request_template.md && echo "Found"
test -f docs/pr_template.md && echo "Found"
If no template exists, offer to use a standard format or create one.
Step 2: Identify the Pull Request
Check current branch for associated PR:
gh pr view --json url,number,title,state 2>/dev/null
If no PR exists, offer to describe changes for a new PR or list open PRs.
Step 3: Gather Comprehensive PR Information
Collect all PR context:
# Full diff of changes
gh pr diff {number}
# Commit history
gh pr view {number} --json commits
# Metadata
gh pr view {number} --json url,title,number,state
For new PRs (not yet created):
git diff main...HEAD
git log main..HEAD --oneline
git diff --name-only main...HEAD
Step 4: Analyze Changes Thoroughly
Deep analysis required - Think carefully about:
- Code changes: Read the entire diff, understand purpose and impact
- User-facing impact: What will users notice? Breaking changes?
- Implementation details: Technical approach and decisions
- Migration requirements: Data migration, deployment steps
Step 5: Handle Verification Requirements
Process checklist items from template:
- Identify automated checks:
npm test,make build, etc. - Run what you can and mark results
- Document what couldn't be completed
Step 6: Generate the Description
Fill out each section from the template:
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.
- 8d ago First seen · 215 lines · 37 tokens per session scan A 3c0f6497c326
pr-description-generator is a skill published in the GitHub repository adrielp/ai-engineering-harness (20 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 37 tokens to every session and 1,250 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 2026-08-30.
Other skills, from other repositories
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
codex-autoresearch
Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…