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 qwerfunch/cladding --skill syncgit clone --depth 1 https://github.com/qwerfunch/claddingWrote 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/qwerfunch/cladding/sync)<a href="https://agentmods.dev/skills/qwerfunch/cladding/sync"><img src="https://agentmods.dev/badge/skills/qwerfunch/cladding/sync/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/qwerfunch/cladding/sync"><img src="https://agentmods.dev/badge/skills/qwerfunch/cladding/sync.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00103 | $0.00456 |
| Opus 5.5 | $0.00041 | $0.00182 |
| Sonnet 5.5 | $0.00021 | $0.00091 |
| Haiku 4.5 | $0.00010 | $0.00046 |
Grade A, and why
sync 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 1mo 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.
What it actually says
Cladding sync
Run clad sync from the project root. The command:
- Loads
spec.yaml(or its sharded form underspec/features/*.yaml). - Validates against
src/spec/schema.json(JSONSchema). - Reports the feature count and any validation failures.
- Exits non-zero when the spec is invalid so CI can gate on it.
Spec must be valid before clad check or any stage runner produces meaningful output. If sync fails, fix the reported issues first.
clad sync
When you actually need it (don't reflex-sync)
You rarely need to run this MANUALLY — and a reflexive "just-in-case" sync after every
operation is wasted work (in an A/B measurement, 28 of 30 manual clad sync calls found
nothing to fix). The inventory + validation are already maintained for you:
clad_create_featureauto-syncs the inventory after each feature it writes (and rejects a malformed AC at creation), so you don't need to sync after creating features.clad check/clad donevalidate the spec themselves (drift stage), so you don't need to pre-sync before them — a real drift surfaces in that gate anyway.
Run clad sync only when you have hand-edited a shard file directly (Edit/Write on
spec/features/*.yaml or spec.yaml), to refresh the inventory and re-validate that edit.
Prefer clad_create_feature over hand-editing in the first place — then even this is unneeded.
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.
- 1mo ago Changed 33222aea324f
- 1mo ago First seen · 34 lines · 103 tokens per session scan A 775c0f990a52
sync is a skill published in the GitHub repository qwerfunch/cladding (16 stars, last pushed 1mo ago), licensed MIT. It adds 103 tokens to every session and 456 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
windows-qa-engineer
Use when testing Windows 11 desktop apps (WinForms/WPF/UWP) via UFO UIA/Win32 automation MCP. Triggers on "test this Windows app", "QA the app", "run smoke test", "click the button", "fill the form", "check the UI", "Windows automation", "UFO QA", "verify the dialog", or any Windows desktop UI testing task. Not for…
linked-intent-dev
Guide for linked-intent development (LID). Consult for ALL code changes. Walks changes through a mode-aware six-phase workflow (HLD → LLD → EARS → intent-narrowing edge audit → tests-first → code) with mandatory stops between each phase. Bugs walk the arrow like any other change — no short-circuit. Enforces cascade…
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code. Enforces red-green-refactor cycle with strict rules.
bug-fix-protocol
8-step disciplined bug-fix protocol that treats every production bug as two failures — the code defect itself and the testing system that allowed it through. Use when fixing a production bug, investigating a regression, writing a post-mortem, or auditing a missed defect. Triggers on "fix this bug", "production bug"…
bidirectional-differential
Audit coherence across an arrow of intent by running two parallel fresh Claude sessions — one reconstructs code from a single EARS, the other reconstructs the EARS from stripped code — then classifies the drift between them. Use when the user invokes /differential-audit, asks to audit EARS-to-code drift for a feature…
auto-loop
TDD-based autonomous development loop with checkpoint recovery and observability changelog.