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 smixs/disruptor-skills --skill converging-and-polishinggit clone --depth 1 https://github.com/smixs/disruptor-skillsWrote 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/smixs/disruptor-skills/converging-and-polishing)<a href="https://agentmods.dev/skills/smixs/disruptor-skills/converging-and-polishing"><img src="https://agentmods.dev/badge/skills/smixs/disruptor-skills/converging-and-polishing/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/smixs/disruptor-skills/converging-and-polishing"><img src="https://agentmods.dev/badge/skills/smixs/disruptor-skills/converging-and-polishing.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 | $0.00117 | $0.04524 |
| Opus 5 | $0.00059 | $0.02262 |
| Sonnet 5 | $0.00023 | $0.00905 |
| Haiku 4.5 | $0.00012 | $0.00452 |
Grade A, and why
converging-and-polishing 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 12d 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 — 339 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Converge and polish
Stage contract
- Stage: 5. Build & converge (the engine — orchestrates 5a
spawning-reviewers, 5bunvibe-review) · Kind: method - Inputs: one slice (from stage 4) — or any artifact to harden.
- Outputs: a converged, hardened artifact on a branch, with a per-iteration trail kept beside the work.
- Entry gate: you have one buildable unit; for a multi-slice build, a fresh session per slice.
- Done when (Mode A bar): two consecutive near-zero passes from cross-family critics
- a final whole-artifact pass, with polish-to-settle after the last destabilizing change. You declare it from the raw findings — never because a reviewer said "looks converged."
- Next: the
qa-demo-standskill — once all slices have converged. - Maintains: —
One loop, two exit policies. The loop turns reviews and cuts into steady, honest improvement. CONVERGE mode runs it until the artifact stops yielding real findings, then stops. ENDLESS mode never stops on its own — it rotates across a project and exits only on an explicit human signal.
REQUIRED SUB-SKILLS — this skill orchestrates two others; load and use them, don't reinvent them:
spawning-reviewers— how to run one honest, neutral, adversarial review. Every review-and-fix iteration below IS a spawning-reviewers pass. The loop is only ever as good as the reviews feeding it, so a biased or rubber-stamp review makes the whole loop lie to you about convergence.unvibe-review— how to find what to cut, unify, or reframe. Every cut pass below IS an unvibe-review pass.
This skill does not re-explain either — it only sequences them over many iterations. If they aren't already loaded, load them first.
The loop unit (both modes share this)
The atom is one iteration:
neutral review by a cross-family critic → fix the real findings → verify → record.
Then iterations are grouped:
~5 review-and-fix iterations (the ratchet) → 1 cut pass (the file) → repeat.
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.
- 12d ago First seen · 339 lines · 117 tokens per session scan A 7208f7556f2f
converging-and-polishing is a skill published in the GitHub repository smixs/disruptor-skills (18 stars, last pushed 2mo ago), licensed MIT. It adds 117 tokens to every session and 4,524 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
todos
This chat has a shared, live TODO plan — your tasks for the conversation, which the user also edits. Read this skill and reach for the todo tools whenever a request takes more than a couple of steps. It covers the plan model (group = task, items = its steps; loose items are the user's lane), how to work it: propose…
writing-workflow-skills
Use when adding a new workflow skill to pi-thinkrail-workflow, changing an existing workflow skill's role, trigger, handoff, or structure, or checking a workflow skill against the workflow system's rules. Not for authoring general-purpose skills outside this package.
debug
Run /debug to find and fix a bug's root cause: a test failing for an unclear reason, /check verify finding a failure, or behavior being wrong. Runs a reproduce, localize, hypothesize, test, fix, verify loop, makes the minimal fix, and hands a regression test to /test. No features, no extra refactors.
setting-up-a-project
Use whenever asked to set up, onboard, initialize, or spec a project — the front door when the workspace has no spec graph yet (brand-new or an existing codebase); also seeded by the app's Set-up-project card (/skill:setting-up-a-project). Not for feature work in an already-specced project — use the brainstorming…
writing-specs
Use when a workflow step drafts or revises a spec artifact — a goal-and-requirements, an architecture, or a module SPEC — or when a workflow skill names it at such a step. The shared quality bar for specs — not a workflow, nothing to execute.
animate
Build a web animation: whether it should animate at all, the purpose, the tool, the properties, the easing curve, the duration, interruption and exit. Writes the CSS or Motion code for dropdowns, modals, toasts, tooltips, accordions, press feedback, stagger and scroll reveals. Use to animate something or make a…