lean-web
Skill2 starsChanged 55 days agoMITView on GitHub
Runs token-efficient defensive web application security reviews for Cursor and Codex. Inventories cookie, CORS, CSP, CSRF, and proxy config, then reports compact header and sink fixes. Use when the user asks for web security, OWASP, XSS, CSRF, CORS, CSP, cookie flags, HTTP security headers, or browser/API web hardening. Do not use for exploits, payloads, bypasses, attacking live sites, or unauthorized scanning.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- linsaftw/lean-agentstheir own version, first seen Nov 1, 2026
- Lean-LLM/lean-agentstheir own version, first seen Oct 25, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- Lean-LLM/lean-agents★ 30same name
- linsaftw/lean-agents★ 30same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository21 other files it gives its agents.
- lean-cryptoSkill
- lean-mobileSkill
- lean-privacySkill
- lean-secSkill
- lean-a11ySkill
- lean-depsSkill
- lean-docsSkill
- lean-perfSkill
- lean-reviewSkill
- lean-ciSkill
- lean-cloudSkill
- lean-costSkill
- lean-hardeningSkill
- lean-iotSkill
- lean-netSkill
- lean-dfirSkill
- lean-ir-playbookSkill
- lean-malwareSkill
- lean-osintSkill
- lean-phishSkill
- lean-threat-modelSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 26
Do not crawl live sites. Do not paste full nginx/Caddy files or HAR dumps.
- Very specific: line 34
Default lean. standard for a named app/route.
- Very specific: line 44
Run scope and headers. Read stdout only.
- Distinctive: line 52
Do not hit third-party URLs, fuzz, or authenticate to systems the user did not open in this workspace.
- Distinctive: line 53
No secret values. No full config pastes.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Lean Web
Defensive web review with a hard context budget. Scripts inventory config; you confirm a few sinks; you patch only when asked.
Let SKILL_ROOT be the folder that contains this SKILL.md. Prefer python3; on Windows use py -3.
python3 "$SKILL_ROOT/scripts/lean_web.py" scope .
python3 "$SKILL_ROOT/scripts/lean_web.py" headers .Do not crawl live sites. Do not paste full nginx/Caddy files or HAR dumps; use trim if a tool is noisy.
python3 "$SKILL_ROOT/scripts/lean_web.py" trim --chars 2500 path/to/out.txtMode
Default lean. standard for a named app/route. deep only if the user says audit/thorough.
| Mode | Budget |
lean | scripts + up to 8 slices; load references/browser.md; ≤6 findings |
standard | + references/api.md; up to 16 slices; ≤10 findings |
deep | needed refs only; ≤16 findings |
Workflow
- Run
scopeandheaders. Read stdout only. - Hotspots: cookie/session code, CORS, CSP, CSRF, file upload, HTML sinks, reverse-proxy config.
rgfirst, then slice-read. Cap quotes at 12 lines.- Report, then stop unless asked to patch.
Hard rules
- Defense only: location, impact, fix. No payloads, bypass strings, or attack reproduction.
- Do not hit third-party URLs, fuzz, or authenticate to systems the user did not open in this workspace.
- No secret values. No full config pastes.
Report template
## Lean-web (`<mode>`)
**App:** <origin or package> | **Budget:** files_read=<n>
| Sev | Location | Issue | Fix |
|-----|----------|-------|-----|
| HIGH | file:line | one clause | one concrete patch |Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.