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 agentmods add skills/calneymgp/solodev/dev-codingnpx skills add calneymgp/solodev --skill dev-codinggit clone --depth 1 https://github.com/calneymgp/solodevWhat 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 | $0.00135 | $0.02072 |
| Opus 5 | $0.00068 | $0.01036 |
| Sonnet 5 | $0.00027 | $0.00414 |
| Haiku 4.5 | $0.00014 | $0.00207 |
Grade C, and why
dev-coding scanned grade C with 2 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 2d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Vai rodar comando destrutivo (force push, drop table, rm -rf) Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
4. Cheque cada `acceptance` — grep / curl / output esperado 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.
/dev-coding — Executar PLAN.md task por task
Esta skill assume que existe .plans/<feature>/PLAN.md produzido por /dev-plan (ou compatível). Executa uma task por vez, com verificação dura no fim de cada uma.
Pré-condições
- Existe
<workspace>/.plans/<feature>/PLAN.md(ou usuário aponta o path) - Você pode escrever e executar comandos no projeto
Se não houver PLAN.md, pare e sugira /dev-plan antes. Se for bug isolado sem plano, sugira /dev-fix.
Ritual de início de sessão
Na primeira execução da sessão (e após cada reset de contexto):
PLAN: <feature> — [████████░░░░] 4/9 tasks ✅
Próxima: task-05 (<tipo>, effort <S/M/L>) — <título>
1 mensagem, depois execute. O usuário sempre sabe onde está sem perguntar.
Processo por task
1. Carregue o contexto mínimo
- Read
.plans/<feature>/PLAN.mdintegralmente - Read
CLAUDE.mddo projeto + sub-CLAUDEs citados em## Affected Areas - Identifique a próxima task com
status: [ ]cuja dependência (depends_on) já está[x] - Read todos os
read_firstda task escolhida ANTES de qualquer edit
2. Despache pelo tipo
type: auto (execução direta)
- Anuncie em 1 frase: "task-XX: <título> — vou tocar ."
- Execute as subtasks da
actionem ordem - Rode o
must_pass(typecheck, build, test, lint conforme aplicável) - Cheque cada
acceptance— grep / curl / output esperado - Marque
[x]em cada acceptance no PLAN.md - Atualize
## Status Logcom timestamp + identificador (commit hash se for committar) - Reporte ao usuário em 2-3 linhas: o que mudou, o que verificou, próxima task
type: tdd (red-green-refactor vertical)
Princípio: tracer bullets, NÃO horizontal slicing. UM teste → UMA implementação → REPETE. Nunca escrever todos os testes primeiro.
Por subtask:
RED: escreva 1 teste para 1 behavior — rode → vê falhar
GREEN: código mínimo para passar — rode → vê passar
(não antecipe próximos testes; não adicione features especulativas)
[Após todas as subtasks GREEN: REFACTOR — só quando GREEN, nunca quando RED]
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.
- 2d ago First seen · 159 lines · 135 tokens per session scan C e881f7a1507b
dev-coding is a skill published in the GitHub repository calneymgp/solodev (2 stars, last pushed 2mo ago), licensed MIT. It adds 135 tokens to every session and 2,072 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
karpathy-guidelines
Tool-agnostic behavioral guidelines for AI coding assistants. Use when writing, reviewing, debugging, or refactoring code to reduce overengineering, surface ambiguity, make surgical changes, and define verifiable success criteria.
Evolve-Skill
核心进化技能。在开发结束时调用，自动分析对话历史，将“项目进化资产”沉淀到 EVOLVE.md，并将平台特有的 AI 行为教训写入 CLAUDE.md / GEMINI.md / AGENTS.md / CURSOR.md，实现可审计、可复用的持续进化。触发词："总结经验"、"进化"、"evolve"、"复盘"、"summarize lessons"、"retrospective"、"postmortem"。不适用于仅完成简单查询、单文件小改动或未产生可沉淀资产的场景。.
metrics-instrumentation
Specification for instrumenting an opik-backend workflow with operational OpenTelemetry metrics — per-stage throughput/latency/error counters and native histograms, dimensioned per-customer (workspace). Use when a pipeline (scoring, ingestion, experiments, jobs) needs per-stage visibility. Covers metric emission only…
happiness-skill
当用户问「怎么才能更幸福/为什么得到了还不满足/怎么减少焦虑」时调用。 核心理念: 幸福是缺憾感清空的默认状态, 是可训练的技能; 欲望是与自己的契约(得到前不快乐), 同时只留一个重大欲望; 活在当下。 不适用于: 临床抑郁等需要专业治疗的场景(本书方法不能替代医疗)。 Triggers: 幸福/不快乐/欲望/焦虑/知足/活在当下/happiness/desire/anxiety.
api-design
REST/GraphQL/gRPC API design best practices. Use when designing APIs, defining contracts, handling versioning. Covers OpenAPI 3.2, GraphQL Federation, gRPC streaming.
setup-matt-pocock-skills
为本仓库配置工程技能——设置其 issue tracker、分诊标签词汇表和领域文档布局。首次使用其他工程技能前运行一次。.