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 Traves-Theberge/openlens --skill using-openlensgit clone --depth 1 https://github.com/Traves-Theberge/openlensWrote 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/traves-theberge/openlens/using-openlens)<a href="https://agentmods.dev/skills/traves-theberge/openlens/using-openlens"><img src="https://agentmods.dev/badge/skills/traves-theberge/openlens/using-openlens/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/traves-theberge/openlens/using-openlens"><img src="https://agentmods.dev/badge/skills/traves-theberge/openlens/using-openlens.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 | $0.00000 | $0.01191 |
| Opus 5.5 | $0.00000 | $0.00476 |
| Sonnet 5.5 | $0.00000 | $0.00238 |
| Haiku 4.5 | $0.00000 | $0.00119 |
Grade A, and why
using-openlens 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 2mo 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What openlens is
openlens is an AI code review tool. It runs four agents (security, bugs, performance, style) in parallel against git diffs. Each agent reads the full codebase, not just the diff. Results include file, line, severity, confidence, and suggested fixes.
When to use which command
Someone asks you to review code:
openlens run --staged # if they have staged changes
openlens run --unstaged # if they have uncommitted changes
openlens run --branch main # if they want to review a full branch
Pick based on what they have. If unsure, --staged is the default. Add --no-verify for speed (skips the false-positive filter).
Someone asks for a quick security check:
openlens run --staged --agents security --no-verify --no-context
Fast. Only runs the security agent. No full file context, no verification pass.
Someone wants to test a single agent they're building:
openlens agent test my-agent --staged --verbose
Someone wants to set up openlens in their project:
openlens setup # interactive wizard: config, agents, hooks, plugins, CI/CD
openlens setup --yes # accept all defaults, no prompts
Someone wants a dry run (no API calls):
openlens run --dry-run --staged
Shows which agents would run, which files changed, what settings are active. No model calls.
How to read the output
Each issue has:
- severity:
critical(must fix),warning(should fix),info(suggestion) - confidence:
high,medium,low(how sure the agent is) - file:line: exact location
- title: one-line summary
- message: detailed explanation
- fix: how to resolve it
- patch: suggested diff (if available)
Exit codes matter:
0= no critical issues (or no issues at all)1= critical issues found2= runtime error (openlens itself failed)
What to do when issues are found
- Show the user the full output
- For critical issues: offer to fix them. Use the
fixfield andpatchfield as guidance - For warnings: mention them but don't block. Ask if the user wants to address them
- For info: note them briefly. These are style suggestions, not problems
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.
- 2mo ago First seen · 152 lines · 0 tokens per session scan A 183444e4bf29
using-openlens is a skill published in the GitHub repository Traves-Theberge/openlens (6 stars, last pushed 11d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,191 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 skills, from other repositories
hunk-launch-video
Produces Hunk videos by driving the real TUI headlessly in a PTY, compositing captioned 1080p frames in Chromium, and encoding with ffmpeg. Use for feature demos, workflow explainers, announcements, launch videos, and full-release roundups.
hunk-release
Prepares, publishes, verifies, and curates Hunk releases. Use for release metadata, benchmarks, tags, publishing, release videos, backports, or recovery.
code-review
Reviewing code for defects: diff-first reading, severity classification, evidence over inference, finding caps, and terminal verdicts. Use when reviewing a diff, PR, or patch, or auditing someone else's work.
responding-to-review
Answering review findings: verify each claim before implementing, no performative agreement, per-item fix/reject/defer with evidence, one batched remediation round. Use when responding to review or remediation rounds.
shadow-verify
Dispatch a parallel adversarial verifier wave after any high-stakes sub-agent investigation (code reviews, audits, findings reports, large refactors, gap analyses) — or whenever a sub-agent asserts a claim with high-confidence language, since confidence is a trigger, not a verdict. Use when sub-agent output will drive…
consumer-map
Read-only consumer graph and blast-radius analysis — takes either a diff (PR number, patch file, git diff) or a named target (symbol, module, config key) and maps the full consumer surface: direct callers, transitive importers (depth 2), test/config/schema refs, hot paths, and event-pipeline members. Emits a scored…