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 pegasi-ai/reins --skill skillgit clone --depth 1 https://github.com/pegasi-ai/reinsWrote 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/pegasi-ai/reins/skill)<a href="https://agentmods.dev/skills/pegasi-ai/reins/skill"><img src="https://agentmods.dev/badge/skills/pegasi-ai/reins/skill.svg" alt="Measured on agentmods" 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 | $0.00090 | $0.01444 |
| Opus 5 | $0.00045 | $0.00722 |
| Sonnet 5 | $0.00018 | $0.00289 |
| Haiku 4.5 | $0.00009 | $0.00144 |
Grade C, and why
reins scanned grade C with 3 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 8d 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.
Reaches for credential filesmediumPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
`~/.openclaw/reins`, `/etc/passwd`, `/etc/shadow` Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- BLOCKED always: `rm -rf /`, `mkfs`, `dd` to disk device, fork bombs Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- LOGGED: `git push`, `pip install`, `npm install`, `curl`, `wget` How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reins — Runtime Security for Claude Code
Reins enforces deterministic security policies on every agent action via Claude Code. PreToolUse and PostToolUse hooks. Policies are pulled from Watchtower (app.pegasi.ai) and evaluated in <50ms with no LLM in the enforcement path.
Use reins for all commands and paths.
Step 1: Verify installation
reins --version
If the command is not found, run:
npm install -g @pegasi/reins && reins init
reins init runs an interactive wizard that:
- Chooses your security level: permissive / balanced / strict
- Selects modules to protect: FileSystem, Shell, Browser, Network
- Installs PreToolUse + PostToolUse hooks into
.claude/settings.json - Prompts for optional Watchtower connection (centralized policy + audit)
- Runs an initial environment security scan (
reins scan)
How hooks work
PreToolUse fires before every Bash, Edit, MultiEdit, Write, and MCP tool call.
| Hook exit | Meaning | What to do |
|---|---|---|
0 |
ALLOWED — proceed normally | Continue |
2 |
BLOCKED — policy violation | Stop. Explain the block. Suggest a safe alternative. Do NOT retry. |
0 + JSON decision: WARN |
WARNING — elevated risk | Acknowledge the warning. Proceed with extra caution. |
PostToolUse fires after every action (non-blocking). It appends a JSONL entry to
~/.openclaw/reins/decisions.jsonl and queues it for Watchtower batch upload.
What gets enforced
Shell (Bash tool)
- BLOCKED always:
rm -rf /,mkfs,ddto disk device, fork bombs - BLOCKED (user-overridable):
DROP TABLE/DATABASE,TRUNCATE,DELETEwithout WHERE,git push --force,kill -9, pipe-to-shell (| bash,| sh) - WARNED:
rm,chmod,chown,sudo,UPDATEwithout WHERE,git reset --hard - LOGGED:
git push,pip install,npm install,curl,wget
File operations (Edit / MultiEdit / Write)
- Writes blocked to protected paths:
~/.ssh,~/.gnupg,~/.env,~/.openclaw/reins,/etc/passwd,/etc/shadow
What ships with it
1 file 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.
- 8d ago First seen · 138 lines · 90 tokens per session scan C 9643a7312cf9
reins is a skill published in the GitHub repository pegasi-ai/reins (408 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 90 tokens to every session and 1,444 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 3 findings (reaches for credential files, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
writing-plan-docs
Write planning documents for new permit0 features, integrations, or significant changes. Use when the user asks to plan, design, spec, or write a plan for a new integration, pack, feature, or architectural change in the permit0 repository.
reviewing-plan-docs
Review planning documents by reading the plan docs and doing a thorough codebase walkthrough, then writing detailed review docs. Use when the user asks to review, audit, critique, or validate a plan, design doc, or spec in the permit0 repository.
revising-plan-docs
Revise planning documents based on design review feedback. Reads review docs, critically assesses each finding (agree or disagree with reasoning), then edits the plan docs accordingly or explains why no change is needed. Use when the user asks to revise, update, address feedback, or incorporate review comments into…
reviewable-demo
Reviewable synthetic skill that fetches a remote template before processing notes.
signet
Cryptographic signing for every tool call with Ed25519 audit trail.
safe-greeting
Returns a short greeting without using tools or external resources.