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 agentmods add skills/avinashp/agentsatlas/creating-prnpx skills add AvinashP/AgentsAtlas --skill creating-prgit clone --depth 1 https://github.com/AvinashP/AgentsAtlasWrote 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/avinashp/agentsatlas/creating-pr)<a href="https://agentmods.dev/skills/avinashp/agentsatlas/creating-pr"><img src="https://agentmods.dev/badge/skills/avinashp/agentsatlas/creating-pr.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 | $0.00036 | $0.01230 |
| Opus 5 | $0.00018 | $0.00615 |
| Sonnet 5 | $0.00007 | $0.00246 |
| Haiku 4.5 | $0.00004 | $0.00123 |
Grade A, and why
creating-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 4d 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 — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creating PR Skill
Create pull requests with clear descriptions that enable efficient reviews.
The Iron Law
NO PR WITHOUT PASSING TESTS
Before creating any PR, verify tests pass. No exceptions.
Workflow
1. Verify Tests Pass (MANDATORY)
Run full test suite before anything else:
# Run tests and verify output
npm test # or pytest, go test, etc.
# Check exit code
echo $? # Must be 0
If tests fail: Fix them first. Do not proceed to PR.
2. Verify Branch State
# Check current branch
git branch --show-current
# Ensure all changes committed
git status
# Check commits to be included
git log main..HEAD --oneline
# Check diff against target branch
git diff main...HEAD --stat
3. Push Branch
# Push and set upstream
git push -u origin <branch-name>
4. Analyze Changes
Understand the full scope:
- What commits are included?
- What files changed?
- What's the user-visible impact?
# View all commits
git log main..HEAD
# View full diff
git diff main...HEAD
5. Write PR Description
Title format:
<type>: <short description>
Keep under 72 characters. Use imperative mood.
Description structure:
## Summary
Brief explanation of what this PR does and why.
## Changes
- Bullet point of key changes
- Another change
- Third change
## Testing
How to test this PR:
1. Step one
2. Step two
3. Expected result
## Verification
- [x] All tests pass
- [x] Linting passes
- [ ] Manual testing completed
## Notes for Reviewers
- Any specific areas to focus on
- Known limitations
6. Create the PR
gh pr create --title "type: description" --body "$(cat <<'EOF'
## Summary
What and why.
## Changes
- Change 1
- Change 2
## Testing
1. How to test
2. Expected result
## Verification
- [x] All tests pass
EOF
)"
Quick Reference
PR Title Prefixes
| Prefix | When to Use |
|---|---|
feat: |
New feature |
fix: |
Bug fix |
refactor: |
Code restructuring |
docs: |
Documentation |
test: |
Test changes |
chore: |
Maintenance |
perf: |
Performance |
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.
- 4d ago First seen · 284 lines · 36 tokens per session scan A 94d67916ab95
creating-pr is a skill published in the GitHub repository AvinashP/AgentsAtlas (7 stars, last pushed 3mo ago), licensed MIT. It adds 36 tokens to every session and 1,230 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
vibe-research
Deep research and market validation for app ideas. Use when starting a new project, validating an idea, or when the user says "research my idea", "validate my app", or "help me start a new project".
trellis-brainstorm
Guides collaborative requirements discovery before implementation. Creates task directory, seeds PRD, asks high-value questions one at a time, researches technical choices, and converges on MVP scope. Use when requirements are unclear, there are multiple valid approaches, or the user describes a new feature or complex…
kn-research
Use when you need to understand existing code, find patterns, search project knowledge, investigate current external facts, or explore a large codebase before implementation.
trellis-session-insight
Reach into past AI conversation history through the trellis mem CLI. Use whenever the user asks 'how did we solve X last time', 'have we discussed this before', 'what was the decision on X', 'remind me what we did in this task', '上次怎么解的', '之前讨论过吗', '想起一段对话', or when starting a brainstorm that overlaps prior work…
kn-init
Use at the start of a new session to read project docs, understand context, and see current state.
trellis-channel
Use Trellis channel for live multi-agent collaboration, spawned workers, cross-agent review, progress inspection, forum channels, and channel log debugging.