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/jansenanalytics/claudex/skillgit clone --depth 1 https://github.com/JansenAnalytics/claudexWhat 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 | $0.00013 | $0.00340 |
| Opus 5 | $0.00006 | $0.00170 |
| Sonnet 5 | $0.00003 | $0.00068 |
| Haiku 4.5 | $0.00001 | $0.00034 |
Grade B, and why
skill 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 yesterday.
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.
2. **Verify the skill exists:** `ls ~/.claude-agent/.claude/skills/<skill-name>/SKILL.md`. If it doesn't, say so and (if jq + skill-index.json available) suggest the 3 closest matches by name. What it actually says
The argument is <skill-name> [args...]. Force-load that specific skill and execute it with the given arguments, regardless of whether the description matching would have picked it up.
Steps:
- Parse the argument: first word is the skill name, rest are passed as args/intent.
- Verify the skill exists:
ls ~/.claude-agent/.claude/skills/<skill-name>/SKILL.md. If it doesn't, say so and (if jq + skill-index.json available) suggest the 3 closest matches by name. - Read the skill's SKILL.md in full — load its instructions into your reasoning context.
- Execute the skill following its instructions, applying the remaining argument as the user's request/input to that skill.
- Return the result in the format the skill specifies (or Telegram-friendly if unspecified).
When to use this command vs. just stating intent:
- The auto-selector picked the wrong skill and you want to force a specific one
- You're testing a new or experimental skill
- The skill name is shorter than describing what you want (e.g.
/skill weather Oslovs. typing out "give me the weather for Oslo")
If the skill body says it requires support files in scripts/, references/, or assets/, use the conventional $CLAUDE_SKILLS_DIR/<skill-name>/... path (default ~/.claude-agent/.claude/skills/).
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.
- yesterday First seen · 23 lines · 13 tokens per session scan B 63813a8a662c
skill is a command published in the GitHub repository JansenAnalytics/claudex (5 stars, last pushed 2mo ago), licensed MIT. It adds 13 tokens to every session and 340 once invoked, about $0.0001 per session on Opus 5. 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 2026-08-31.
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.