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.
git clone --depth 1 https://github.com/sergeyklay/.agentsWrote 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/commands/sergeyklay/.agents/make-pr)<a href="https://agentmods.dev/commands/sergeyklay/.agents/make-pr"><img src="https://agentmods.dev/badge/commands/sergeyklay/.agents/make-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/commands/sergeyklay/.agents/make-pr"><img src="https://agentmods.dev/badge/commands/sergeyklay/.agents/make-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 | $0.00010 | $0.00502 |
| Opus 5.5 | $0.00004 | $0.00201 |
| Sonnet 5.5 | $0.00002 | $0.00100 |
| Haiku 4.5 | $0.00001 | $0.00050 |
Grade A, and why
make-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 1mo 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Your task is to commit staged changes and manage pull requests (PR).
Task
- Use
git-commitAgent Skill to create commits, create a branch, andcreate-prAgent Skill to open/change a PR with a meaningful title and description - Incorporate provided details or context about the changes
- Detect whether you need to create a new PR or update an existing one based on context
- Stage only relevant files - never
git add -Awithout reviewing what would be included - When updating, verify the PR description still accurately reflects the changes
- Use Conventional Commits messages when appropriate
Template Enforcement
MANDATORY: Before creating any PR:
- Check for the PR template: Use PR template provided by the
create-prAgent Skill. You MUST follow it. - Read the template completely: Read the entire template file to understand its structure
- Follow the template exactly: Structure the PR body to match the template's sections verbatim
- Use the template headings as-is (including emojis if present)
- Fill in each section following the guidance provided
- Do not skip sections or reorder them
- DO NOT invent a custom format: Deviation from it is a failure
Process:
- Load
create-prAgent Skill - Read regarding PR template
- Read template described in Agent Skill
- Map changes to template sections
- Create PR body matching template structure
- Verify sections match before creating/updating PR
PR Description Content Rules
- DO NOT reference
TODO.md,.specs/*.mdor.plans/*.mdin the PR description. Those belong in specs and plans, not in the git history. - DO NOT add an "Implementation Details" or "References" section beyond what the template defines.
- ONLY fill in the sections defined by the PR template - nothing more.
Constraints
- Never force-push without explicit user confirmation.
- Never push directly to
main- always use a feature branch. - Never skip pre-commit hooks (
--no-verify). - If a hook fails, fix the underlying issue and create a new commit.
- Apart from fixing a failed hook, DO NOT run tests, write code, validate solution, etc. Your task SOLELY is to create PR.
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.
- 1mo ago Changed · +1 lines bd56e1cf3562
- 1mo ago First seen · 49 lines · 10 tokens per session scan A 9dd03b18c1a7
make-pr is a command published in the GitHub repository sergeyklay/.agents (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 10 tokens to every session and 502 once invoked, about $0.0000 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 2026-08-31.
Other commands, from other repositories
cm
Stage working tree changes and create a Conventional Commit (no push).
cp
Stage, commit, and push the current branch following git governance rules.
commit-and-create-mr
Commit and create MR on Gitlab, with post-merge worktree cleanup.
review
Recent git commits: !git log --oneline -10.
orient-commit
Draft a git commit message (what / why / findings) for review before committing.
commit
Create well-formatted commits with conventional commit messages and emoji.