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/mathieu0905/skilllens/skillscopegit clone --depth 1 https://github.com/mathieu0905/skilllensWhat 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 | $0.00367 |
| Opus 5 | $0.00000 | $0.00183 |
| Sonnet 5 | $0.00000 | $0.00073 |
| Haiku 4.5 | $0.00000 | $0.00037 |
Grade A, and why
skillscope 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 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.
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.
What it actually says
SkillScope
Capture the current Claude Code run for SkillScope skill coverage analysis, then open the SkillScope browser UI.
Use When
- The user asks whether a
SKILL.md, rule, or instruction file was actually followed. - The user wants a SkillScope report for a Claude Code session.
- The user wants to compare with-skill vs no-skill or success vs failure trajectories.
Required Inputs
Ask for missing paths instead of guessing:
- Claude Code session trace JSONL/JSON.
- Loaded
SKILL.md,CLAUDE.md, project rule, memory, or playbook file paths. - Optional task prompt file or result JSON.
Command
From the SkillScope repository root:
npm run capture -- \
--agent claude_code \
--trace <claude-session.jsonl> \
--skill <path-to-SKILL.md> \
--task <optional-task.md> \
--result <optional-result.json> \
--out skillscope.capture.json
Then analyze:
npm run analyze -- --bundle skillscope.capture.json --out skillscope-report
If this command file is used from the SkillScope checkout, use the shared capture CLI directly:
npm run capture -- \
--agent claude_code \
--trace <claude-session.jsonl> \
--skill <path-to-SKILL.md> \
--out skillscope.capture.json
Then run npm run open to launch the browser UI if it is not already open.
Boundaries
- Do not claim AI-based analysis unless an LLM judge pass was explicitly configured.
- The default analyzer is heuristic and local.
- Confirm loaded skill paths whenever possible; discovered files are weaker provenance.
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 · 56 lines · 0 tokens per session scan A 8df7be4f6b81
skillscope is a command published in the GitHub repository mathieu0905/skilllens (2 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 367 tokens. 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 commands, from other repositories
e2e
使用 Playwright 对 Web UI 进行端到端测试（支持视频录制、Trace 录制、控制台/网络日志捕获）.
auto-browse
Auto-browse — learn, optimize, and graduate browser operations or web data-mining workflows.
research-perplexity
Run a deep research query using Perplexity's /research mode via Playwright browser automation. This is an alternative to /export-to-council that uses Perplexity's dedicated research mode instead of multi-model council.
review
Compare a reference design against an implementation. Accepts Figma URL, image file, or browser URL as reference.
graphify
Turn your vault into a clustered knowledge graph with HTML and JSON outputs.
laravel-playwright
E2E Playwright patterns; use the laravel:e2e-playwright skill exactly as written.