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/luongnv89/asm/skill-install-improvednpx skills add luongnv89/asm --skill skill-install-improvedgit clone --depth 1 https://github.com/luongnv89/asmWrote 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/luongnv89/asm/skill-install-improved)<a href="https://agentmods.dev/skills/luongnv89/asm/skill-install-improved"><img src="https://agentmods.dev/badge/skills/luongnv89/asm/skill-install-improved.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 | $0.00059 | $0.03510 |
| Opus 5 | $0.00030 | $0.01755 |
| Sonnet 5 | $0.00012 | $0.00702 |
| Haiku 4.5 | $0.00006 | $0.00351 |
Grade C, and why
skill-install-improved scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf "$SKILL_PATH/.asm-improver" How it starts
The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Install Improved
You install an improved variant of one skill instead of the skill as published: resolve the target to a local directory → run skill-auto-improver on it → install the improved result → report what was improved and from what. The improvement is a step inside the install, not a separate errand. One skill per run.
When to Use
- The user says "install
<skill>but improve it first" or "install an improved version of<skill>" - The user points at a catalog skill below the 85/8 floor and wants the better version on their machine
- The user has a local or cloned skill directory and wants the improved variant installed, not the raw one
Do not trigger for: improving without installing (skill-auto-improver), contributing upstream (skill-upstream-pr), authoring from scratch (skill-creator), plain installs (asm install <source>), or bulk-improving many skills at once.
Prerequisites
Verify each before resolving anything. Stop and tell the user if any fails.
asmandgiton PATH- Python 3 and
~/.claude/skills/skill-creator/scripts/quick_validate.py—skill-auto-improverrequires it - Network access to GitHub, for the repo and name forms
- Write access to the install target — the directory for the chosen tool and scope (for
claude:~/.claude/skills/global,.claude/skills/project). Other tools install elsewhere; take the real path fromasm list --jsonor the install output.
The user's own files are never modified (design decision)
Every input form is improved on a throwaway copy under $(mktemp -d) — local paths included. Deliberate: an install that rewrites the user's working copy is a side effect they did not ask for, skill-auto-improver mandates git fetch + git pull --rebase before any edit (against a local path that rebases their branch), and copying makes all forms behave identically.
Trade-off: the improvement lands only in the installed copy, not the user's tree. The copy has no origin and no history, so the improver's mandatory repo sync is inapplicable and is skipped — nothing to clobber, nothing pushed. Say so out loud when you skip it. To persist the change, point them at skill-auto-improver (their path) or skill-upstream-pr (the source repo).
What ships with it
3 files 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 · 192 lines · 59 tokens per session scan C 415cd5af6497
skill-install-improved is a skill published in the GitHub repository luongnv89/asm (908 stars, last pushed today), licensed MIT. It adds 59 tokens to every session and 3,510 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment.
finishing-a-development-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work.
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code.
receiving-code-review
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation.