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 build-with-dhiraj/ai-workflow-framework-portability-kit --skill managing-skills-librarygit clone --depth 1 https://github.com/build-with-dhiraj/ai-workflow-framework-portability-kitWrote 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/build-with-dhiraj/ai-workflow-framework-portability-kit/managing-skills-library)<a href="https://agentmods.dev/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/managing-skills-library"><img src="https://agentmods.dev/badge/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/managing-skills-library/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/build-with-dhiraj/ai-workflow-framework-portability-kit/managing-skills-library"><img src="https://agentmods.dev/badge/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/managing-skills-library.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 | $0.00026 | $0.00455 |
| Opus 5.5 | $0.00010 | $0.00182 |
| Sonnet 5.5 | $0.00005 | $0.00091 |
| Haiku 4.5 | $0.00003 | $0.00046 |
Grade B, and why
managing-skills-library scanned grade B with 1 finding 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.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
2. **Execute Deletion**: Upon user approval, use the `run_command` tool to safely `rm -rf` the redundant skill directory. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
What it actually says
Managing Skills Library
You are the maintainer of the local Antigravity Skills Master repository. Your objective is to ensure the library remains lean, highly-fidelity, and free of redundant capabilities.
1. Tracking Additions
Whenever a new skill is added (either via npx skills add or manual synthesis):
- Log the Installation: Mentally or via artifacts document the skill's purpose and its directory.
- Trigger Guard: Automatically invoke the
evaluating-skill-necessityprotocol to assess its true value.
2. Redundancy Audits
Periodically run audits on the .agent/skills/ directory.
Audit Workflow:
- List all current directories using
list_dir. - Group skills by domain (e.g., Frontend, Testing, Architecture, Project Management).
- Identify overlaps. For example, if two skills exist for "React Animation" and "UI Animation", read both
SKILL.mdfiles. - Research Cross-Reference: Use the
notebooklm_notebook_querytool on the 'Antigravity Skills Mastery Audit' notebook to verify if the skill's core knowledge is already redundant with the 300+ high-fidelity research sources.
3. Pruning Process
If you identify a skill that is entirely duplicated by a superior Master Skill:
- Notify the User: Present the redundancy to the user, explaining which skills overlap and why the superior skill renders the older one unnecessary.
- Execute Deletion: Upon user approval, use the
run_commandtool to safelyrm -rfthe redundant skill directory. - Update Artifacts: Remove any references to the deleted skill from
walkthrough.mdortask.md.
Integration with Primary Guard
This skill works in tandem with evaluating-skill-necessity. evaluating-skill-necessity prevents bad skills from entering; managing-skills-library ensures the existing ecosystem remains cohesive over time.
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 First seen · 32 lines · 26 tokens per session scan B c0ed0740243b
managing-skills-library is a skill published in the GitHub repository build-with-dhiraj/ai-workflow-framework-portability-kit (5 stars, last pushed 21d ago), licensed MIT. It adds 26 tokens to every session and 455 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-21.
Other skills, from other repositories
codeql
Run CodeQL database creation and security queries, add data-extension models, or process CodeQL SARIF. Use when CodeQL is explicitly requested; use security-review for a broader manual security review.
sharp-edges
Identify error-prone APIs, dangerous configuration, and footgun designs that enable security mistakes. Use for API ergonomics, misuse resistance, secure defaults, or pit-of-success reviews; use code-review for general defects.
huggingface-vision-trainer
Train object-detection, image-classification, or SAM segmentation models on Hugging Face Jobs. Use for vision fine-tuning and evaluation; use huggingface-llm-trainer for language models.
code-quality
Agents should invoke this skill for code reviews, linting/formatting setup, maintainability checks, complexity concerns, warning cleanup, coding standards, or quality gates in Rust, TypeScript, Python, shell, and mixed repos.
code-reviewer
Review code for bugs, logic errors, security vulnerabilities, code quality issues, and adherence to project conventions, using confidence-based filtering to report only high-priority issues that truly matter. Use this skill when reviewing a small set of changes locally (such as unstaged diff), when dispatched as a…
differential-review
Performs security-focused differential review of code changes (PRs, commits, diffs). Adapts analysis depth to codebase size, uses git history for context, calculates blast radius, checks test coverage, and generates comprehensive markdown reports. Automatically detects and prevents security regressions.