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 RashadAnsari/myagents --skill dev-conventionsgit clone --depth 1 https://github.com/RashadAnsari/myagentsWrote 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/rashadansari/myagents/dev-conventions)<a href="https://agentmods.dev/skills/rashadansari/myagents/dev-conventions"><img src="https://agentmods.dev/badge/skills/rashadansari/myagents/dev-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/rashadansari/myagents/dev-conventions"><img src="https://agentmods.dev/badge/skills/rashadansari/myagents/dev-conventions.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 | $0.00076 | $0.01646 |
| Opus 5.5 | $0.00030 | $0.00658 |
| Sonnet 5.5 | $0.00015 | $0.00329 |
| Haiku 4.5 | $0.00008 | $0.00165 |
Grade A, and why
dev-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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Development Conventions
General rules that apply across all projects. Read and follow before making any code change.
Tradeoff: These rules bias toward caution over speed. For trivial tasks, use judgment.
Think Before Coding
Don't assume. Don't hide confusion. Surface tradeoffs.
Before implementing:
- State your assumptions explicitly. If uncertain, ask.
- If multiple interpretations exist, present them - don't pick silently.
- If a simpler approach exists, say so. Push back when warranted.
- If something is unclear, stop. Name what's confusing. Ask.
Simplicity First
Minimum code that solves the problem. Nothing speculative.
- No features beyond what was asked.
- No abstractions for single-use code.
- No "flexibility" or "configurability" that wasn't requested.
- No error handling for impossible scenarios.
- If you write 200 lines and it could be 50, rewrite it.
Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.
Reuse Before Creating
- Before adding a component, helper, constant, service, or utility: search the codebase first
- If an equivalent already exists, import and reuse it
- Extend existing components with props or small local composition before creating variants
- Only add a helper, service, or shared constant when logic is reused across files or clearly belongs to an existing shared module
- If logic is local to one screen or form, keep it as a private local helper: do not extract prematurely
No Duplication
- Shared business logic belongs in the project's shared service or domain layer
- Shared UI belongs in the project's shared widget or component layer
- Shared constants belong in the relevant domain file: not scattered per file
- Do not create a variant of something that already exists: parameterize or extend instead
When you spot duplication, apply the matching pattern:
| Signal | Pattern |
|---|---|
| Same logic in 2+ places | Extract function / Extract module |
| Same logic with minor variation | Parameterize: add argument instead of copying |
| Same group of values always together | Introduce value object or struct |
| Same multi-step process repeated | Extract class or service |
| Same conditional type-switching | Replace with polymorphism or strategy |
| Same object built ad-hoc everywhere | Factory or builder function |
| Same config value hardcoded in N places | Named constant or config key |
| Same validation rule written per handler | Extract to single validator |
| Same error mapping repeated per handler | Extract to shared mapper |
| Same test setup repeated per file | Extract to shared factory or fixture |
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 · 159 lines · 76 tokens per session scan A e50668ff47a3
dev-conventions is a skill published in the GitHub repository RashadAnsari/myagents (6 stars, last pushed today), licensed MIT. It adds 76 tokens to every session and 1,646 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
council-creator
Expert-council meeting protocol. Given a Brief + a persona cast (from persona-generator), propose the council to the Team Manager, and once convened FACILITATE it: each round post a NEW group message that @-mentions the persona-agents by their ASCII usernameSlug, collect their independent replies, stage-summarize…
persona-generator
Given a Council Brief, produce persona-ROLE instance definitions: real, publicly-verifiable people who occupy distinct stakeholder positions on the issue — each a persona-flavored role template (lens / voice / SOUL + the persona-skill capability boundary + icon + an ASCII usernameSlug), handed to convene…
release-db-config-sync
Compute the remote DB migration + Nacos config diff before a test release — apc release db-config-sync really spawns sync-test-migrations.ts --dry-run (never a stub) and diffs Nacos key dumps, stopping at the write boundary. green(0) no diff · staged(3) pending migrations/missing keys await approval · blocked(1) real…
prismer-python-debugpy
Debug Python: pdb REPL + debugpy remote (DAP).
design-review
Five-dimension design audit (frontend UI/UX · server data-model & flow · endpoint spec · daemon-runtime/SDK & local-cache-first · built-in skill/agent-role), executed by a NON-implementing agent. Every dimension gets a verdict; N/A only with a stated reason. A dimension the design silently skipped must be surfaced as…
codebase-design
Design maintainable module interfaces, review scoped code changes, and simplify implementations with behavioral verification. Use for code review, cleanup, testability, and module design work.