Boring and invisible security layer for your coding agent. Open Sourced
Joined October 2025
- Tweets 2,475
- Following 720
- Followers 507
- Likes 5,305
417 Photos and videos
Pinned Tweet
May 18
Prismor is a self-improving security layer for AI agents and modern supply chain defense
Developers don't need a new SaaS, the future of secure software development is all local
Prismor lets you:
- redact secrets so agents dont read them
- secure supply chain package consumption
- skill and mcp scanning for prompt injection
- scan and fix vulnerabilities (safely and validated)
- all agent executions in a local self-serve dashboard
All open source!
8
2
27
27,332
This is great! Replacing huge LOCs with a library of package is smart, however is it secure? @DietrichGebert we've built an OSS simple engine to check for it, let's collaborate on this
🚨 A dev got so frustrated watching his AI agent write 500 lines for a 5-line problem that he built a fix.
He named it Ponytail.
Named after the guy every team has: long ponytail, oval glasses, been there longer than the version control!
The one who looks at your 50-line pull request, says nothing, and replaces it with a single line.
Ponytail is a ruleset and plugin that injects this exact mindset into AI coding agents.
Before writing anything, the agent now actively looks for a reason not to.
The before and after is stark:
- Ask a standard agent for a date picker, and it builds a custom wrapper component with a stylesheet.
- Ask a Ponytail-equipped agent, and it just writes <input type="date">.
The benchmarks against unconstrained models (Haiku, Sonnet, Opus) are impressive:
→ 80–94% less code generated
→ 47–77% cheaper execution
→ 3–6x faster task completion
It works across the modern AI stack, with rules and plugins for Cursor, Windsurf, Cline, Copilot, Aider, and Claude Code.
The best code is the code you never wrote.
100% free and open-source.
repo link below ↓
35
19h
Replies to X DMs are slow but we're working on it! So if we're late in responding then sorry?
We're pro-AI but bots are never the answer to dev-rel
There's a human behind this account
2
21
Jun 13
Repo deleted because it had all commits from claude Fable 5
Jun 13
The US government, citing national security authorities, has issued an export control directive to suspend all access to Fable 5 and Mythos 5 by any foreign national, whether inside or outside the United States, including foreign national Anthropic employees.
The net effect of this order is that we must abruptly disable Fable 5 and Mythos 5 for all our customers to ensure compliance.
Access to all other Claude models is not affected.
We apologize for this disruption to our customers. We believe this is a misunderstanding and are working to restore access as soon as possible.
Read our full statement: anthropic.com/news/fable-myt…
5
10
9,355
Jun 12
May 2026: an attacker shipped a package with valid SLSA attestations and genuine OIDC tokens. immunity-agent blocked it anyway
The scorer caught a behavioral signal and the install script accessed credential env vars.
We also switched from NVD to osv in v1.6.0. NVD was matching the wrong package versions and lagging weeks behind registry advisories.
Immunity-agent is an open source invisible layer for AI agents for secure terminal executions
1
4
130
Jun 12
1
41
Jun 9
Anthropic naming their models
Introducing Claude Fable 5: a Mythos-class model that we’ve made safe for general use.
Its capabilities exceed those of any model we’ve ever made generally available.
1
57
Jun 8
You just wanna drink a morning cup of your coffee and crank claude --dangerously-skip-permissions
This is fun and totally safe if you're using immunity-agent. FOSS 👇
3
2
221
Jun 8
1
77
Jun 8
We love crack3d teenagers and boomers who care for code security!
Hello 17.2% and 7.8% and 1.6%
3
2
142
Jun 6
139