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/byronxlg/skillfoldnpx agentmods add skills/byronxlg/skillfold/skillfold-cliWrote 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/byronxlg/skillfold/skillfold-cli)<a href="https://agentmods.dev/skills/byronxlg/skillfold/skillfold-cli"><img src="https://agentmods.dev/badge/skills/byronxlg/skillfold/skillfold-cli/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/byronxlg/skillfold/skillfold-cli"><img src="https://agentmods.dev/badge/skills/byronxlg/skillfold/skillfold-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, 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 34 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.
- medium Agent Snooping · line 3 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 8 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Rogue Agent · line 34 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00043 | $0.00736 |
| Opus 5.5 | $0.00017 | $0.00294 |
| Sonnet 5.5 | $0.00009 | $0.00147 |
| Haiku 4.5 | $0.00004 | $0.00074 |
Grade A, and why
skillfold-cli 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skillfold CLI
You use skillfold, a declarative skill manager for agent skills. Projects declare the skills they use in skillfold.yaml; skillfold installs them for the selected tools and pins exact revisions in skillfold.lock.
Manifest
skillfold.yaml at the project root:
skills:
commit-helper: ./skills/commit-helper # local directory
frontend-design: github:owner/repo/path/to/[email protected] # GitHub (tag, branch, or SHA)
planning: npm:skillfold/[email protected] # npm package
compose:
reviewer:
description: Review code changes together with their tests.
use: [code-review, testing]
A trailing @ref after the last / pins a version. For a skill shipped inside a tool's npm package, @installed (e.g. npm:<package>/<skill>@installed) follows the version the project has installed: bump the dependency, run skillfold install, and the skill re-pins. Composed skills concatenate the bodies of the skills they use into one generated skill.
Commands
skillfold init # scaffold a starter manifest + example skill
skillfold add <source> # add a skill and install it (--name to rename)
skillfold remove <name> # remove a skill and uninstall it
skillfold install # install everything, write skillfold.lock
skillfold install --frozen # CI mode: exact lockfile install, fail on drift
skillfold update [name...] # re-resolve moving refs, then reinstall
skillfold check # verify manifest, lockfile, and installed files agree
skillfold list # status table (ok / modified / not installed / not locked / stale)
skillfold info <name> # source, pin, hash, and install path for one skill
skillfold search [query] # find skill packages on npm
Add -g / --global to use ~/.config/skillfold/skillfold.yaml (or $XDG_CONFIG_HOME/skillfold/skillfold.yaml). Global skills install into the selected tools' user-level directories, including ~/.claude/skills, ~/.agents/skills, and ~/.cursor/skills. Run skillfold migrate -g to copy a legacy ~/.claude config, preserving pins and relative source paths.
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 2d9b7dd028e5
- 1mo ago Changed · -1 tokens per session 542278974eed
- 1mo ago Changed · +6 tokens per session 2efd42ced4a5
- 2mo ago First seen · 52 lines · 38 tokens per session scan A c5a03904544b
skillfold-cli is a skill published in the GitHub repository byronxlg/skillfold (15 stars, last pushed 6d ago), licensed MIT. It adds 43 tokens to every session and 736 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
migrate-to-shoehorn
Migrate test files from as type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace as in tests, or needs partial test data.
typescript
Apply when writing TypeScript code. Strict types, discriminated unions, async patterns, and runtime safety.
writing-great-skills
Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable. Read it before writing or changing a skill.
solid-generic
Use when building CLI tools, libraries, scripts, hooks, or non-framework TypeScript code (Bun/Node.js -- SOLID, files within FUSESOLIDMAXLINES, JSDoc mandatory).
mcp-server-patterns
Build MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API.
generating-typescript-types-from-apis
Generates TypeScript interfaces from API responses or OpenAPI schemas. Use when the user asks about typing API responses, creating interfaces from JSON, parsing Swagger/OpenAPI, or keeping types in sync with backend.