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 gpsaggese/helpers --skill github.find_name_for_prgit clone --depth 1 https://github.com/gpsaggese/helpersWrote 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/gpsaggese/helpers/github.find_name_for_pr)<a href="https://agentmods.dev/skills/gpsaggese/helpers/github.find_name_for_pr"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/github.find_name_for_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/gpsaggese/helpers/github.find_name_for_pr"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/github.find_name_for_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 | $0.00011 | $0.00769 |
| Opus 5.5 | $0.00004 | $0.00308 |
| Sonnet 5.5 | $0.00002 | $0.00154 |
| Haiku 4.5 | $0.00001 | $0.00077 |
Grade A, and why
github.find_name_for_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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal
- Given the current Git branch, find a title and a short description to push the changes as a Pull Request
Workflow
Read Rules
- Read rules about:
- Coding:
.claude/skills/coding.rules.md - Unit tests:
.claude/skills/testing.rules.md
- Coding:
Read the Changes in the Current Git Client
-
Get the changed files:
git diff --name-status origin/master HEAD ... -
Analyze the diff against
master(ororigin/master):git diff master...HEAD --name-only # or if master is not available locally: git diff origin/master...HEAD --name-only
Propose the Description of the PR
- Propose a one-line title for the PR
- It must be Linux friendly: no
&or non-alphanumeric chars
- It must be Linux friendly: no
- Save it into
pr_title.txt
Propose the Description of the PR
- Write
pr_commit_msg.txtwith a short list of changes in the format
where each## <Description of the change> - Change1 - Change2<ChangeN>is a one or two line bullet describing what changed related to<Description of the change> - Use plaintext only, no markdown formatting
- Use nested bullets, not numbered bullets
- Wrap lines under 85 chars
Write the Description of the PR
- Write
pr_description.mdfollowing the template.claude/templates/github_PR_description.template.md - Say in
pr_description.mdhow it was generated, with this comment at the top:<!-- Generated by `.claude/skills/github.find_name_for_pr/SKILL.md` --> - Fill every section from the diff and from the plan or spec the PR closes
- Write "N/A: " for a section that does not apply
- Do not invent test counts or results: run the tests or ask the user
- Follow
.claude/skills/markdown.rules.mdand.claude/skills/text.rules.md
Example
This PR consolidates major infrastructure updates adding developer tools,
standardized documentation templates, and improved onboarding workflows for the
helpers_root ecosystem.
Stats: 192 files changed, 4985 insertions, 2218 deletions
- **Documentation**: Added CONTRIBUTING.md with contribution guidelines and
task_instructions.md for task execution workflow
- **Figure Creation Skills**: Added 3 new figure-related skills (create_svg, create_tikz,
make_professional) with rules
- **Templates**: Added github_PR_plan.template.md and architecture_doc.template.md for
standardized documentation
- **Tooling**: Added scripts for figure compression, image downloading, and git utilities
(find_junk.sh, git_backup_branch.sh)
- **Onboarding**: Added bounty spam prevention guide for team onboarding
- **Skill Updates**: Improved descriptions and workflows across 120+ skill files with
consistent formatting
- **Helper Improvements**: Enhanced hdaemon.py and hselect_input_output.py with extended
functionality
- **Linting**: Updated cc_lint.py with additional linting capabilities
- **Documentation Cleanup**: Removed legacy instr.md and consolidated command rules
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 · 94 lines · 11 tokens per session scan A 530561914593
github.find_name_for_pr is a skill published in the GitHub repository gpsaggese/helpers (158 stars, last pushed today), licensed Apache-2.0. It adds 11 tokens to every session and 769 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 2026-11-06.
github.find_name_for_pr compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| github.find_name_for_prgpsaggese/helpers | Skill | 158 | today | Apache-2.0 | A | 11 | Claude Code |
| create-prprisma/orm | Skill | 48k | today | Apache-2.0 | A | 48 | Claude Code, Codex |
| git-commitThinkInAIXYZ/deepchat | Skill | 6.4k | yesterday | Apache-2.0 | A | 15 | Claude Code, Codex |
| repo-syncdavidondrej/skills | Skill | 4.3k | yesterday | MIT | A | 25 | Claude Code, Codex |
| engineer-bot-opsmakecindy/cindy | Skill | 9.4k | today | Apache-2.0 | A | 57 | Claude Code, Codex |
| mcore-split-prNVIDIA/skills | Skill | 3.9k | today | Apache-2.0 | A | 25 | Claude Code |
| git-commit-writermergisi/awesome-openclaw-agents | Skill | 4.1k | 3d ago | MIT | A | 53 | Claude Code, Codex |