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 telus-labs/stagecraft --skill code-conventionsgit clone --depth 1 https://github.com/telus-labs/stagecraftWrote 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/telus-labs/stagecraft/code-conventions)<a href="https://agentmods.dev/skills/telus-labs/stagecraft/code-conventions"><img src="https://agentmods.dev/badge/skills/telus-labs/stagecraft/code-conventions/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/telus-labs/stagecraft/code-conventions"><img src="https://agentmods.dev/badge/skills/telus-labs/stagecraft/code-conventions.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 | $0.00063 | $0.01491 |
| Opus 5.5 | $0.00025 | $0.00596 |
| Sonnet 5.5 | $0.00013 | $0.00298 |
| Haiku 4.5 | $0.00006 | $0.00149 |
Grade A, and why
code-conventions 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.
How it starts
The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Conventions
This skill contains project-wide coding standards. Agents load this when writing or reviewing code. Do not duplicate these rules in agent prompts.
Each rule is paired with a concrete example. Reviewers cite the rule name (e.g. "BLOCKER: code-conventions #magic-number") so the author can find the rule and the example without context-switching.
General
-
#explicit-over-clever — Code is read more than it is written.
// BAD: clever — what does the !! do? what's the precedence? const isReady = !!user && !!user.config && !!user.config.ready; // GOOD: explicit — reads top-to-bottom. const isReady = user != null && user.config != null && user.config.ready === true; -
#docstring — Every exported function has a docstring/JSDoc.
-
#magic-number — Use a named constant when a literal would otherwise be unexplained.
// BAD: what is 86400000? setTimeout(reload, 86400000); // GOOD: const MS_PER_DAY = 24 * 60 * 60 * 1000; setTimeout(reload, MS_PER_DAY); -
#no-commented-code — No commented-out code in commits. Use git history if you need to remember what was there.
Naming
| Layer | Convention | Example |
|---|---|---|
| Files | kebab-case (all languages) |
user-store.ts, user_store.py, UserStore.kt is wrong |
| Classes / Types | PascalCase |
UserStore, OrderId |
| Functions / variables | camelCase |
getUser, orderCount |
| Constants | SCREAMING_SNAKE_CASE |
MAX_RETRIES, JWT_SECRET |
| Database columns | snake_case |
user_id, created_at |
Error Handling
-
#no-silent-swallow — Never swallow an error without a comment explaining why.
// BAD: error vanishes — why? try { await unlink(tmp); } catch {} // GOOD: intent stated; reviewer can verify it. try { await unlink(tmp); } catch { /* tmp already gone — best-effort cleanup */ } -
#typed-errors — Don't throw bare strings; throw
Error(or a subclass).// BAD: caller can't .message or .stack on a string. if (!user) throw "user not found"; // GOOD: if (!user) throw new NotFoundError(`user ${id} not found`);
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 First seen · 144 lines · 63 tokens per session scan A e0f78d96472d
code-conventions is a skill published in the GitHub repository telus-labs/stagecraft (6 stars, last pushed 19d ago), licensed MIT. It adds 63 tokens to every session and 1,491 once invoked, about $0.0003 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
semantix-guide
Troubleshoot and configure Semantix capabilities: Skills (project/custom/global/builtin priority, discovery dirs), Commands (override order, /dir:file naming), Hooks (11 events, automatic project loading, matchers, timeouts), MCP (semantix-agent.toml + .mcp.json + plugin packages, autostart), plugin packages…
semantix
Install and use the semantix memory kernel as a middleware in your agent: extract user preferences / workflows / experience from past sessions, retrieve and inject them on demand. One binary + your agent's own tools.
intuitive-shape
Shape unsettled product ideas into bounded bets before planning; excludes settled fixes and approved execution.
intuitive-doc
Maintain README.md, ARCHITECTURE.md, STATUS.md, and docs/human/ when they drift or need cleanup.
intuitive-reduce-entropy
Find and rank material simplification candidates when the cleanup target or plan risks are unclear.
research
Investigate a bounded question using multiple sources or a cited report; answer single facts and codebase questions directly.