Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/mgiovani/cc-arsenalnpx agentmods add skills/mgiovani/cc-arsenal/improve-skillWrote 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/mgiovani/cc-arsenal/improve-skill)<a href="https://agentmods.dev/skills/mgiovani/cc-arsenal/improve-skill"><img src="https://agentmods.dev/badge/skills/mgiovani/cc-arsenal/improve-skill.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 47 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
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 | $0.00178 | $0.02299 |
| Opus 5 | $0.00089 | $0.01149 |
| Sonnet 5 | $0.00036 | $0.00460 |
| Haiku 4.5 | $0.00018 | $0.00230 |
Grade A, and why
improve-skill 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 7d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Improve Skill
Take a skill that already exists and bring it up to the current authoring standard: with a frozen baseline and a measured comparison, not just a confident rewrite. Every claim of "better" in your final report must trace to a validator run or a grading result you actually produced this session.
Ground rules
- Snapshot before you touch anything, and never touch the snapshot again. Once
skill-snapshot/exists for a skill, it is read-only for the rest of the run: every later step (rewrite, iteration, feedback pass) reads it for comparison and never writes to it. If a later step wants to "fix" the baseline to make a comparison look better, that is overfitting to the eval, not improving the skill: refuse and explain why. - Never edit an eval's prompt or assertions to make a failing run pass. If a rewritten skill fails an assertion, fix the skill (SKILL.md, references, description) or, if the assertion itself was wrong when it was written, say so explicitly and get the user's sign-off before changing it: silently loosening an assertion after seeing it fail is the one move that makes every later benchmark meaningless.
- Judgment, not rewrite-for-rewrite's-sake. A skill that's already close to the rubric gets a small diff, not a fresh draft. Read it fully before deciding what's actually deficient: most of the value here is in the delta, not the word count changed.
- This skill never commits, pushes, or force-updates anything. Its output is a modified skill directory plus a benchmark report. When the user is ready to save the change, they invoke
git-commitorshipseparately: do not rungit commityourself even if the user says "looks good, ship it," because that phrase in this context is about the skill quality, not a request to commit.
Workflow
1. Scope
Identify which skill(s) to improve: a name the user gave, a path, or "audit all skills" (if a repo-wide audit workflow already exists here, e.g. .claude/workflows/arsenal-audit.js, its per-skill findings are a good prioritized starting list; don't re-derive that scoring yourself, just read its output). For each target, confirm skills/<name>/SKILL.md exists: if it doesn't, stop and say so; this skill only improves skills that already exist (a brand-new skill is create-skill's job).
What ships with it
5 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.
- 7d ago First seen · 103 lines · 178 tokens per session scan A 5e86866cbb68
improve-skill is a skill published in the GitHub repository mgiovani/cc-arsenal (7 stars, last pushed 7d ago), licensed MIT. It adds 178 tokens to every session and 2,299 once invoked, about $0.0009 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
dataforseo
Agent-callable DataForSEO tools — Google SERP results, keyword and domain analytics, backlinks, Google Maps business data, on-page audits, and AI-search visibility (LLM answers + brand mentions). Use when the user wants SEO or AI-search data, even if they don't name DataForSEO.
gitlab
Agent-callable GitLab tools — manage issues and merge requests, review diffs, commit files, run pipelines, and search. Use when the user mentions GitLab or wants to review or merge an MR, commit code, run CI, or manage issues — even if they don't name GitLab explicitly.
algolia
Agent-callable Algolia tools — index records, search and browse them, manage index settings, synonyms, and query rules, and read AI recommendations.
alpaca
Agent-callable Alpaca trading tools — place and manage stock, crypto, and options orders, read account balances, positions, and portfolio history, look up assets and market hours, and read watchlists. Use when the user mentions Alpaca or wants to trade or inspect a brokerage account, even if they don't name Alpaca…
discord
Agent-callable Discord tools — send and manage messages, start threads and forum posts, manage channels, members, and roles, and post via webhooks. Use when the user mentions Discord or wants to post, read, or manage Discord servers, channels, or members, even if they don't name Discord explicitly.
dropbox
Agent-callable Dropbox tools — upload, organize, find, and share files and folders. Use when the user wants to manage Dropbox content (save, move, search, share, list, or read files), including requests that don't name Dropbox explicitly, e.g. "save this report to my cloud storage" or "share that folder with Sam".