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 iteration-loopgit 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/iteration-loop)<a href="https://agentmods.dev/skills/krzysztofsurdy/code-virtuoso/iteration-loop"><img src="https://agentmods.dev/badge/skills/krzysztofsurdy/code-virtuoso/iteration-loop/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/iteration-loop"><img src="https://agentmods.dev/badge/skills/krzysztofsurdy/code-virtuoso/iteration-loop.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 | $0.00067 | $0.02552 |
| Opus 5.5 | $0.00027 | $0.01021 |
| Sonnet 5.5 | $0.00013 | $0.00510 |
| Haiku 4.5 | $0.00007 | $0.00255 |
Grade A, and why
iteration-loop 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.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Iteration Loop
Executes a .code-virtuoso/loop/backlog.json plan one step at a time. The plan is committed and never changes during a run; each step's status, attempts and notes live in .code-virtuoso/loop/state/state.json. Each item is a sequence of steps; the loop advances by step, and an item is verified only when all of its steps are. The defining property of this loop, worth restating before anything else: no agent - worker or reviewer - ever decides that a step is done. A script runs the step's literal verifyCommand and checks its exit code; only that script writes status (item status is never stored - it is derived from the steps). This skill documents how to run the loop and what each outcome means; it does not itself judge completion.
The two modes
| Mode A - session-supervised | Mode B - unattended batch | |
|---|---|---|
| Invoked via | /loop-virtuoso:start |
scripts/run-batch.sh path/to/backlog.json |
| Runs | Inside your current Claude Code session, via a Stop hook |
Fresh claude -p process per iteration |
| Use for | Watching it work, stepping away briefly, backlogs of 5-15 items | Large backlogs, overnight/CI runs |
| Stops automatically when | Backlog exhausted, blocked out, max iterations, stall, or violation limit | Same conditions, plus a cumulative cost cap and a usage/rate-limit guard |
Mode B is intentionally not a slash command - it spawns long-running detached processes that don't fit a single tool-call turn. Run it directly from a terminal, from CI, or from within a session via claude --bg --exec "$(pwd)/scripts/run-batch.sh .code-virtuoso/loop/backlog.json" if you want it tracked as a background job you can claude logs/claude stop.
Participant fidelity differs between modes
A step's participant (see backlog-compiler) is honored with different strength in each mode - state this honestly, the two are not equivalent:
- Mode B spawns a fresh process per step, so it can pass real CLI flags -
--agent <name>for anagentparticipant,--append-system-promptfor apersona- and that invocation genuinely runs as the participant. - Mode A is one continuous session; it can't re-spawn itself per step. It can only ask the model to role-play the participant through the prompt text: delegate via the Task tool for an
agentparticipant, or "act as: …" for apersona. That's a softer instruction, not a hard guarantee of isolation.
What ships with it
2 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.
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 · 103 lines · 67 tokens per session scan A f02ff03e4a04
iteration-loop is a skill published in the GitHub repository krzysztofsurdy/code-virtuoso (36 stars, last pushed yesterday), licensed MIT. It adds 67 tokens to every session and 2,552 once invoked, about $0.0003 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).