# Skillscope

> Launch SkillScope from Codex, capture the active Codex session trace plus loaded skill/rule files, and open the browser coverage viewer.

- **Type:** Skill
- **Install:** `agentstack add skill-mathieu0905-skilllens-skillscope`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [mathieu0905](https://agentstack.voostack.com/s/mathieu0905)
- **Installs:** 0
- **Category:** [Web & Browser](https://agentstack.voostack.com/c/web-and-browser)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [mathieu0905](https://github.com/mathieu0905)
- **Source:** https://github.com/mathieu0905/skilllens/tree/main/integrations/skillscope-codex/skills/skillscope

## Install

```sh
agentstack add skill-mathieu0905-skilllens-skillscope
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# SkillScope For Codex

Use this skill when the user asks to run `/skillscope`, capture Codex skill coverage, inspect which skill instructions were followed, or open the SkillScope browser view for the current Codex session.

## User Entry

The user entry is the Codex slash prompt:

```bash
/skillscope
```

That slash prompt should call the repository launcher:

```bash
npm --prefix  run codex -- --project-cwd "$(pwd)"
```

## Capture Contract

- Identify the Codex rollout JSONL for the active or requested session.
- Prefer the session whose `session_meta.payload.cwd` matches the current project.
- Identify `SKILL.md`, `CLAUDE.md`, `AGENTS.md`, or `*.skill.md` files that the trace proves were read or used.
- If no loaded skill can be proven from tool traces, fall back to project skill discovery and mark those files as discovered rather than confirmed loaded.
- Preserve task prompt, result metadata, model, cwd, agent version, session ID, and inferred session segments when available.
- Generate a `skillscope.capture.json` bundle before running analysis.
- Run SkillScope analysis with the generated bundle, not with separately guessed skill and trace files.
- Open the browser viewer after capture unless `SKILLSCOPE_NO_OPEN=1` or `--no-open` is set.

## Commands For Codex To Run

From any user project, the slash prompt should run:

```bash
npm --prefix  run codex -- --project-cwd "$(pwd)"
```

If the active session cannot be inferred, ask for an explicit trace path and run:

```bash
npm --prefix  run codex -- \
  --project-cwd "$(pwd)" \
  --trace 
```

Optional precise inputs:

```bash
npm --prefix  run codex -- \
  --project-cwd "$(pwd)" \
  --trace  \
  --skill  \
  --task  \
  --result 
```

## Analysis Boundary

- The current default analyzer is heuristic: constraint extraction, trace normalization, keyword overlap, and structured tool signals.
- Do not describe heuristic findings as AI judgment.
- The launcher is responsible for provenance: which session and which skill artifacts are being compared.
- The browser "启动分析" action can run an agent-native judge after the user selects a skill-use window.
- Agent judge runs must follow `skills/skillscope-analyzer/SKILL.md`: judge only the provided local artifacts and cite concrete trace event IDs.
- Do not call a separate model API for SkillScope judge. Codex captures should use Codex; Claude Code captures should use Claude Code.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [mathieu0905](https://github.com/mathieu0905)
- **Source:** [mathieu0905/skilllens](https://github.com/mathieu0905/skilllens)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-mathieu0905-skilllens-skillscope
- Seller: https://agentstack.voostack.com/s/mathieu0905
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.