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 gomilesf/convergo --skill cvg-hybrid-build-loopgit clone --depth 1 https://github.com/gomilesf/convergoWrote 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/gomilesf/convergo/cvg-hybrid-build-loop)<a href="https://agentmods.dev/skills/gomilesf/convergo/cvg-hybrid-build-loop"><img src="https://agentmods.dev/badge/skills/gomilesf/convergo/cvg-hybrid-build-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/gomilesf/convergo/cvg-hybrid-build-loop"><img src="https://agentmods.dev/badge/skills/gomilesf/convergo/cvg-hybrid-build-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 | $0.00080 | $0.02702 |
| Opus 5 | $0.00040 | $0.01351 |
| Sonnet 5 | $0.00016 | $0.00540 |
| Haiku 4.5 | $0.00008 | $0.00270 |
Grade A, and why
cvg-hybrid-build-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 9d 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 — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hybrid Build Loop
Run cvg-build-loop with a tiered engine split: a Codex CLI session
implements, Codex CLI sessions take every first-pass review round, and a
high-taste Claude design model reviews only when the execution tier already
believes the work is clean. The design model is the exit gate inside the
protocol, not a closer bolted on after the loop: its blockers re-enter the
normal feedback cycle.
Prerequisites
- Claude Code as the orchestrating platform: the
Agenttoolmodelparameter andSendMessagecontinuation are required. - A working
codexCLI (codex --versionsucceeds) with the convergo codex plugin installed, so codex sessions can load role skills by name. - Codex sessions run with whatever permissions the user's own codex configuration grants. Convergo passes no sandbox or permission flags; roles assume normal developer access — reading and writing the repo, committing, and running the project's build and test commands.
If either prerequisite fails, stop and report it. Do not silently fall back to a single-engine loop; the user chose this skill for the split.
Engine Bindings
Defaults; the user's invocation may override either tier.
| Tier | Default | Runs |
|---|---|---|
| Execution tier | codex exec -m gpt-5.6-sol at model_reasoning_effort=high — the current frontier codex pin, updated with plugin releases |
worker, first-pass fresh reviews, QA workers |
| Design tier | Claude fable via the Agent tool model parameter |
final-fresh-exit reviews |
Focused re-reviews always return to the reviewer session that raised the findings, on whichever tier that session lives — unchanged protocol.
Before the first spawn, echo the resolved bindings in one line — worker
model and effort, reviewer engine, design-tier model, round cap — so a
binding mistake surfaces before any specialist runs. If codex rejects the
pinned execution-tier model (a retired id), fall back to the model the
user's codex config resolves to — respawn the specialist wrapper with the
model pin dropped, initial -m and resume -c overrides both — echo what
actually ran (the model:
line of the run header, never an assumption), and flag it to the user if
it sits below a frontier model at high reasoning effort: the tier split's
economics assume execution is nearly as capable as the design tier.
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.
- 9d ago First seen · 205 lines · 80 tokens per session scan A 7f9e94b6c184
cvg-hybrid-build-loop is a skill published in the GitHub repository gomilesf/convergo (7 stars, last pushed 1mo ago), licensed MIT. It adds 80 tokens to every session and 2,702 once invoked, about $0.0004 per session on Opus 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 2026-08-31.
Other skills, from other repositories
review-video-with-pingfusi
Have any video reviewed by a real human, through iterative pingfusi review rounds. Use when asked to "review this video", "check the rendered video", "does this video match the prompt/brief", "what do people think of this ad/trailer/demo", or after rendering a Remotion composition or AI-generated clip that no test can…
beautify-with-pingfusi
Beautify or redesign an existing website through iterative pingfusi review rounds with a real human reviewer. Use when asked to "beautify this website," "make this page look professional," "polish this UI/design," "improve the visual design," or finish an AI-built page when there is no reference site to match. Do not…
fix-with-pingfusi
Fix or polish an existing website clone/draft using pingfusi review rounds. Use when the user says "fix it with pingfusi", "polish this clone", "make this match the original", or asks to finish/verify a draft built by any tool (ditto, lovable, v0, hand-written) until the review passes.
pixel-perfect-clone
Clone, copy, or replicate a website/page pixel-perfect using pingfusi. Use when the user asks to clone a site or page with pingfusi, copy a webpage's design, replicate a page, or make a pixel-perfect copy of a URL. Drives the full enforced pipeline - capture, numeric gates, behavior reproduction, and review rounds…
pingfusi-review
Use Pingfusi proactively whenever a coding agent reaches a question it cannot settle with code, automated tests, documentation or search, or a local browser and needs real human judgment or real-world verification. Trigger even when the user does not mention Pingfusi for subjective choices about copy, design, clarity…
agent-review
Create a read-focused external-agent review packet for code, diffs, plans, or generated artifacts.