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 squall-chua/skills --skill sync-bddgit clone --depth 1 https://github.com/squall-chua/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/squall-chua/skills/sync-bdd)<a href="https://agentmods.dev/skills/squall-chua/skills/sync-bdd"><img src="https://agentmods.dev/badge/skills/squall-chua/skills/sync-bdd/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/squall-chua/skills/sync-bdd"><img src="https://agentmods.dev/badge/skills/squall-chua/skills/sync-bdd.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 | $0.00020 | $0.00974 |
| Opus 5.5 | $0.00008 | $0.00390 |
| Sonnet 5.5 | $0.00004 | $0.00195 |
| Haiku 4.5 | $0.00002 | $0.00097 |
Grade A, and why
sync-bdd 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Find the drift between what the project now requires and what the .feature
files still say. Both sides get read in full, because drift hides in what nobody
thought to look at.
1. Fix both sides
Requirements — the current ones. Look in this order: the conversation, the repo
(PRDs, specs, ADRs, README.md, CLAUDE.md), then the project's issue tracker for
anything that changed the behaviour, reached the same way to-bdd step 1 describes.
If nothing states a behaviour, ask the user where the requirements live.
Features — every .feature file in scope.
For a large set, git log on the requirement docs and on the feature directory tells
you which side moved last and narrows where drift is likely. The comparison itself
still covers everything in scope.
Done when: you have both lists — every behaviour the requirements state, and every scenario the feature files specify.
2. Match them
Pair each requirement behaviour with the scenario that covers it. Match on behaviour — actor, trigger, outcome — rather than on wording, since a rename is itself a kind of drift.
Done when: every requirement behaviour and every scenario is either paired or left unpaired on purpose. An item you skipped because it was hard to place is drift you failed to report.
3. Classify the drift
Each unpaired or mismatched item lands in one bucket:
- Uncovered — a requirement behaviour with no scenario. Something the project promises and nothing specifies.
- Stale — a paired scenario that no longer matches its requirement: a changed rule, value, or outcome, or the project's terminology moved on and the scenario kept the old word.
- Orphaned — a scenario with no requirement behind it. Either the behaviour was dropped, or it is real behaviour nobody wrote down. These two need opposite fixes, so name which one you believe it is and why.
Done when: every item from step 2 sits in a bucket, and every stale item quotes the requirement's wording against the scenario's wording.
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 · 106 lines · 20 tokens per session scan A 305d0576bccb
sync-bdd is a skill published in the GitHub repository squall-chua/skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 974 once invoked, about $0.0001 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.
sync-bdd compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sync-bddsquall-chua/skills | Skill | 2 | 1mo ago | MIT | A | 20 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 314k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |