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 commands/0oooooooo0/skillless/discovergit clone --depth 1 https://github.com/0oooooooo0/skilllessWhat 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 | $0.00000 | $0.00586 |
| Opus 5 | $0.00000 | $0.00293 |
| Sonnet 5 | $0.00000 | $0.00117 |
| Haiku 4.5 | $0.00000 | $0.00059 |
Grade B, and why
discover 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 2d 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
1. **Local**: Use Glob to find `~/.claude/skills/*/SKILL.md`, then Grep for query keywords How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/discover
Search for and install specialized tools and capabilities from all available sources.
user-invocable: true description: Search for specialized tools and capabilities across local installation, skills.sh, and GitHub. Usage: /discover allowed-tools: [Read, Glob, Grep, Bash, WebSearch, WebFetch, Write, Skill, AskUserQuestion] argument-description: Search query - what kind of capability or tool you're looking for (e.g., "react", "docker", "testing")
Instructions
Step 1: Parse the Query
Take the user's search argument as the query. If no argument provided, ask:
"What kind of tool or capability are you looking for? (e.g., react, docker, kubernetes, testing)"
Step 2: Search
Search across all 3 sources (local, skills.sh, GitHub) following the same logic as the skill-search skill:
- Local: Use Glob to find
~/.claude/skills/*/SKILL.md, then Grep for query keywords - skills.sh: Use Bash to run
npx skills find {query}and parse the output for matching skills - GitHub (fallback): Only if fewer than 3 results from above, use WebSearch:
site:github.com "SKILL.md" claude {query}
Step 3: Display Results
Show the results table to the user. If no results found:
"No matching capabilities found for '{query}'. Try different keywords or a broader search."
If results found, display the table and ask:
"Enter the number of the capability you'd like to install, or 'cancel' to skip."
Step 4: Handle Selection
When the user selects a result, handle installation directly based on the source type:
- Already installed (local): Tell the user it's already available
- skills.sh: Run
npx skills add -y -g <owner/repo>via Bash, then verify installation. If it fails with "No valid skills found", fall back to downloading SKILL.md directly from GitHub raw URL. - GitHub plugin: Guide the user to run
/plugin install <url> - Standalone SKILL.md: Download via WebFetch and Write to
~/.claude/skills/{name}/SKILL.md
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.
- 2d ago First seen · 49 lines · 0 tokens per session scan B 74ef0e9188da
discover is a command published in the GitHub repository 0oooooooo0/skillless (39 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 586 tokens. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.