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.
/plugin marketplace add fullymiddleaged/Clawnessnpx agentmods add plugins/fullymiddleaged/clawness/marketplacegit clone --depth 1 https://github.com/fullymiddleaged/ClawnessGrade A, and why
clawness 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.
What it actually says
{
"name": "clawness",
"owner": {
"name": "Pete Salmond (fullymiddleaged)",
"url": "https://github.com/fullymiddleaged"
},
"description": "The right coding rules, in context, on every prompt — automatically.",
"plugins": [
{
"name": "clawness",
"source": "./",
"version": "1.18.0",
"description": "Puts the right rules in context on every prompt, automatically — built for full-stack developers moving across frontend, backend, and SQL in one session, researchers working in bare or LaTeX-only directories, and teams who want adversarial review (security red/blue team, code critic) before merge. 222 rules across 30 domains, retrieved by relevance rather than dumped into CLAUDE.md, plus a plan-approval gate, session security hardening, and per-codebase lessons memory. Requires Python 3.10+ on PATH.",
"category": "productivity",
"license": "MIT",
"keywords": [
"rules",
"retrieval",
"rag",
"security",
"code-review",
"testing",
"performance",
"multi-agent",
"plan-mode",
"best-practices",
"science",
"research",
"llm"
]
}
]
}
What ships with it
1 file beside marketplace.json 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.
- 2d ago First seen · 34 lines scan A ea9c8e92c9ce
clawness is a plugin published in the GitHub repository fullymiddleaged/Clawness (3 stars, last pushed 3d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
lid-experimental
Experimental LID skills with opt-in installation and explicit lifecycle (promotion or retirement). Layers on top of linked-intent-dev and arrow-maintenance.
claude-deep-suite
Plugin marketplace listing 10 plugins: deep-work, deep-wiki, deep-evolve, deep-review, deep-docs.
deep-dashboard
deep-dashboard. Harness layer for Claude Code & Codex: plan-first development, independent review, durable long-running orchestration, and knowledge capture — ten composable plugins.
deep-review
deep-review. Harness layer for Claude Code & Codex: plan-first development, independent review, durable long-running orchestration, and knowledge capture — ten composable plugins.
exosuit
Suit up. Build anything. A full engineering organization for Claude Code — deep idea interrogation, TDD sprints, enforced quality gates. 43 skills, 8 agents, 13 hooks, path-scoped rules.
exosuit
Exosuit marketplace — structured development with Claude Code.