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 vnnkl/agentflywheel --skill bead-polishinggit clone --depth 1 https://github.com/vnnkl/agentflywheelWrote 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/vnnkl/agentflywheel/bead-polishing)<a href="https://agentmods.dev/skills/vnnkl/agentflywheel/bead-polishing"><img src="https://agentmods.dev/badge/skills/vnnkl/agentflywheel/bead-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/vnnkl/agentflywheel/bead-polishing"><img src="https://agentmods.dev/badge/skills/vnnkl/agentflywheel/bead-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 | $0.00113 | $0.02624 |
| Opus 5.5 | $0.00045 | $0.01050 |
| Sonnet 5.5 | $0.00023 | $0.00525 |
| Haiku 4.5 | $0.00011 | $0.00262 |
Grade A, and why
bead-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 2mo 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 — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bead Polishing
Iteratively refine a task breakdown through multiple review rounds until the tasks converge. Works with any task format: beads, GitHub issues, user stories, PRD tasks, todo lists.
Why This Matters
The Three Reasoning Spaces cost model:
| Space | Rework Cost | Example |
|---|---|---|
| Plan | 1x | Fix a markdown document |
| Task definitions | 5x | Rewrite and re-link beads/issues |
| Code | 25x | Debug, refactor, retest |
Fixing a vague task description takes 30 seconds. Fixing the code that a vague description produced takes 30 minutes. Polishing task definitions until they are airtight is the single highest-ROI activity in the entire workflow.
A task breakdown that "looks done" after one pass almost always contains duplicates, gaps, broken dependencies, and underspecified acceptance criteria. These defects are invisible until an agent starts coding and produces the wrong thing. Polishing exposes them while the fix is still cheap.
Process Overview
[Task breakdown exists]
|
v
Round 1: Structural audit
|
v
Round 2: Coverage + dependency check
|
v
Round 3: Description depth pass
|
v
Round 4: Adversarial review
|
v
Round 5+: Only if convergence < 75%
|
v
[Polished, converged task set]
Run 4-6 rounds. Each round applies ALL checks but emphasizes a different lens. Track convergence after each round. Stop when convergence reaches ~75% (diminishing returns appear around 90%).
Before Starting
Identify the task source. Ask the user if unclear:
- Beads:
.beads/beads.jsonlorbd list --json - GitHub Issues:
gh issue listwith a milestone or label filter - PRD user stories: A markdown file with
US-XXXentries - prd.json: A JSON file with
userStoriesarray - Other: Any structured list of tasks with titles and descriptions
Read the source plan (the PRD or design doc the tasks were derived from). Polishing without the source plan is guessing. If no source plan exists, ask the user for the intent document or feature description.
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.
- 2mo ago First seen · 288 lines · 113 tokens per session scan A 3451c86f97c5
bead-polishing is a skill published in the GitHub repository vnnkl/agentflywheel (2 stars, last pushed 5mo ago), licensed MIT. It adds 113 tokens to every session and 2,624 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
dev-console-context
Use when the user mentions Developer Console, projects, workspaces, credentials, or orgs — or uses phrases like "show my projects", "list workspaces", "get credentials", "switch project", "which org", "my org", "console", "navigate", "explore", "what projects do I have", "show credentials", "what workspace". Also use…
ring:mapping-feature-relationships
Mapping how features relate and phasing the work: categorizing PRD features, grouping them into domains, charting cross-feature journeys, dependencies, and integration points, and defining the binding Phases that plan.md mirrors one-to-one at Gate 7. Gate 2 of ring:planning-large-features; runs after…
remove
Remove a deployed framework or addon from the current workspace.