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 krzysztofsurdy/code-virtuoso --skill hooks-and-guardrailsgit clone --depth 1 https://github.com/krzysztofsurdy/code-virtuosoWrote 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/krzysztofsurdy/code-virtuoso/hooks-and-guardrails)<a href="https://agentmods.dev/skills/krzysztofsurdy/code-virtuoso/hooks-and-guardrails"><img src="https://agentmods.dev/badge/skills/krzysztofsurdy/code-virtuoso/hooks-and-guardrails/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/krzysztofsurdy/code-virtuoso/hooks-and-guardrails"><img src="https://agentmods.dev/badge/skills/krzysztofsurdy/code-virtuoso/hooks-and-guardrails.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 | $0.00058 | $0.01734 |
| Opus 5.5 | $0.00023 | $0.00694 |
| Sonnet 5.5 | $0.00012 | $0.00347 |
| Haiku 4.5 | $0.00006 | $0.00173 |
Grade A, and why
hooks-and-guardrails 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 yesterday.
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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hooks and guardrails
An instruction in a rules file is a request. A hook is code that runs whether or not the model remembers the request. Use rules to say what you want, deny rules and the sandbox to set hard limits, and hooks to catch what slips through and to give the agent fast feedback on its own work.
Core principles
| Principle | Meaning |
|---|---|
| Enforce, do not ask | Anything that must never happen belongs in a deny rule or the sandbox, not in prose |
| Layers fail differently | Deny rules cover the agent's file tools, the sandbox covers shell processes, hooks cover custom logic. Use at least two for secrets |
| Hooks are sensors | A hook that returns the error to the agent turns a silent failure into a fix in the same turn |
| Fast or off | A hook that takes seconds on every edit gets disabled. Keep per-edit checks under a second or two |
| Hooks run with your permissions | A hook script is code the agent can trigger. Review it like any other script, and never let it run untrusted input through a shell |
Procedure
-
Pick a risk level. Choose the row that matches the work, then set the permission mode and sandbox to match.
Risk Typical work Mode and isolation Low Own repo, no secrets nearby, no untrusted content Accept-edits style mode plus deny rules Medium Real project, credentials on the machine, reads issues or docs from the web Default prompts or classifier mode, OS sandbox on, deny rules, hooks below High Unknown repo, unattended runs, CI, or untrusted input plus network access Container or VM with no secrets mounted, allowlisted network, pre-approved tools only, no bypass flags on the host Bypass-everything flags belong only inside an isolated container or VM. See deny-rules-and-modes for the settings per tool.
-
Add deny rules for secret files and risky commands. Deny rules win over allow rules and over a hook's allow. They do not stop a script that opens the file by itself, which is why step 3 and the sandbox exist.
What ships with it
9 files 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.
- references/claude-code-settings.md 7.4 KB
- references/codex-hooks.md 5.3 KB
- references/deny-rules-and-modes.md 4.6 KB
- scripts/block-secret-reads.sh 2.2 KB runs code
- scripts/post-edit-check.sh 1.5 KB runs code
- scripts/prompt-reminder.sh 1.5 KB runs code
- scripts/reinject-context.sh 1.1 KB runs code
- scripts/stop-gate.sh 1.2 KB runs code
- scripts/test-hooks.sh 10 KB runs code
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.
- yesterday Changed · +4 lines 6961d7f08d35
- 2d ago First seen · 93 lines · 58 tokens per session scan A 1caed9825792
hooks-and-guardrails is a skill published in the GitHub repository krzysztofsurdy/code-virtuoso (36 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 1,734 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-22.
Other skills, from other repositories
hermes-diagnostic-review
Use when running a read-only diagnostic review of recent Hermes sessions to find recurring mistakes, failed tool calls, and repeated fixes, then propose suggestion-only improvements and reusable skills. Human-gated; never auto-applies.
instruction-eval
Change one condition an agent runs under (instruction text, the reference material instructions point at, MCP tools and permissions, hooks, skill files), then run the same prompts before and after, several times each, to see what actually changes. Produces an HTML report showing both arms' answers side by side. Use…
worth-building
Decide how elaborate to build something (simple vs. robust) and return a concrete, PoC-shaped proposal at that level — not over- or under-engineered, but right-sized. Use whenever someone is building something and the investment level is unclear: "quick or proper?", "MVP vs. real product", "is this over-engineering?"…
django-ticket-triage
Analyze a Django Trac ticket and produce a triage recommendation report — duplicate search, related PRs, forum threads, and the affected source code. Use when the user gives a Django ticket number, or asks whether a ticket is valid, a duplicate, or ready for a triage stage.
gh-issues
Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5]…
healthcheck
Host security hardening and risk-tolerance configuration for OpenClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, risk posture, exposure review, OpenClaw cron scheduling for periodic checks, or version status checks on a machine running OpenClaw (laptop, workstation, Pi, VPS).