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 skills add JoelYYoung/retrolens --skill retrolens-plugingit clone --depth 1 https://github.com/JoelYYoung/retrolensWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/joelyyoung/retrolens/retrolens-plugin)<a href="https://agentmods.dev/skills/joelyyoung/retrolens/retrolens-plugin"><img src="https://agentmods.dev/badge/skills/joelyyoung/retrolens/retrolens-plugin/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/joelyyoung/retrolens/retrolens-plugin"><img src="https://agentmods.dev/badge/skills/joelyyoung/retrolens/retrolens-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00040 | $0.04468 |
| Opus 5 | $0.00020 | $0.02234 |
| Sonnet 5 | $0.00008 | $0.00894 |
| Haiku 4.5 | $0.00004 | $0.00447 |
Grade B, and why
retrolens 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 10d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
find ~ -name "*.jsonl" -path "*/.claude/*" -maxdepth 6 2>/dev/null | head -20 This is a copy
89% identical to retrolens — 36 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 485 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RetroLens — AI Conversation Log Navigator
Navigate AI agent conversation logs like a debugger. Point at a log directory, list sessions, then drill into turns, tool calls, and raw data.
Recommended Flow
The typical workflow follows these steps. Each step has a corresponding command (for Claude Code) and a detailed workflow section below.
/retrolens → Discover log locations, see what's available
↓
/retrolens:connect → Choose a project, connect to its logs, verify
↓
/retrolens:analyze → Pick session(s), drill into turns, map phases
↓
/retrolens:reflect → Extract human lessons + agent directives
For non-Claude-Code agents, follow the same flow using the Workflow sections (A → B/C → D) directly.
Quick Start
First check whether retrolens is already installed:
retrolens --version
If the command is found, proceed to CLI Commands below.
If not found, ask the user which option they prefer:
-
Already installed — retrolens is installed but not on PATH. Ask the user where/how it was installed (e.g., which venv, conda env, or directory), then help activate the correct environment or adjust PATH.
-
Agent installs — let the agent install it. Ask the user which method to use:
Method Command pip pip install retrolensuv uv pip install retrolenspipx pipx install retrolensRun the selected command and verify with
retrolens --version. -
Install manually — the user will install it themselves. Provide the install options above for reference and wait for them to confirm it's ready.
CLI Commands
cfg — Set Working State (Do This First) ⭐
retrolens cfg set --path /path/to/logs # Set log directory (auto-detects format)
retrolens cfg set --source vscode # Override detected source type
retrolens cfg set --reader ./reader.py # Register a custom reader
retrolens cfg show # View current config
retrolens cfg clear # Reset to defaults
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 485 lines · 40 tokens per session scan B b96a1695e714
retrolens is a skill published in the GitHub repository JoelYYoung/retrolens (2 stars, last pushed 4mo ago), licensed MIT. It adds 40 tokens to every session and 4,468 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). It is 89% identical to retrolens, differing in 36 lines, and is treated as a copy.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.