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 skills/mathieu0905/skilllens/skillscopenpx skills add mathieu0905/skilllens --skill 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 | $0.00031 | $0.00633 |
| Opus 5 | $0.00015 | $0.00316 |
| Sonnet 5 | $0.00006 | $0.00127 |
| Haiku 4.5 | $0.00003 | $0.00063 |
Grade A, and why
skillscope scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SkillScope For Codex
Use this skill when the user asks to run /skillscope, capture Codex skill coverage, inspect which skill instructions were followed, or open the SkillScope browser view for the current Codex session.
User Entry
The user entry is the Codex slash prompt:
/skillscope
That slash prompt should call the repository launcher:
npm --prefix <skillscope-repo> run codex -- --project-cwd "$(pwd)"
Capture Contract
- Identify the Codex rollout JSONL for the active or requested session.
- Prefer the session whose
session_meta.payload.cwdmatches the current project. - Identify
SKILL.md,CLAUDE.md,AGENTS.md, or*.skill.mdfiles 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.jsonbundle 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=1or--no-openis set.
Commands For Codex To Run
From any user project, the slash prompt should run:
npm --prefix <skillscope-repo> run codex -- --project-cwd "$(pwd)"
If the active session cannot be inferred, ask for an explicit trace path and run:
npm --prefix <skillscope-repo> run codex -- \
--project-cwd "$(pwd)" \
--trace <codex-rollout.jsonl>
Optional precise inputs:
npm --prefix <skillscope-repo> run codex -- \
--project-cwd "$(pwd)" \
--trace <codex-rollout.jsonl> \
--skill <path-to-SKILL.md> \
--task <optional-task.md> \
--result <optional-result.json>
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.
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 · 70 lines · 31 tokens per session scan A 0009ac8d9f69
skillscope is a skill published in the GitHub repository mathieu0905/skilllens (2 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 633 once invoked, about $0.0002 per session on Opus 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 2026-08-31.
Other skills, from other repositories
mcporter
List, auth, and call MCP servers/tools from the terminal.
agent-messaging
Send and receive cryptographically signed messages between AI agents using the Agent Messaging Protocol (AMP). Use when the user asks to "send a message to an agent", "check agent inbox", "message another agent", "reply to a message", "notify an agent", or any inter-agent communication task.
📝 任务完成后归档
重要提醒: 每次完成复杂调试或开发任务后，主动执行此流程！ 将学到的经验归档为 skill，供以后参考。不要等用户提醒。.
oracle
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
agent-mode
Unified tool for managing agent LLM modes (add, remove, update, list, switch).
agento11y-prod-setup
Sets up production evaluation and guardrails for a DEPLOYED AI agent in Grafana Agent Observability, grounded in the agent's own code and its real ingested traffic. The judgment layer on top of the agento11y skill: it reads the agent's source (system prompt, tools, entrypoint) AND samples its live traffic via gcx…