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 lsantosweb/codex-agents-skills-kit --skill backend-specialistgit clone --depth 1 https://github.com/lsantosweb/codex-agents-skills-kitWrote 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/lsantosweb/codex-agents-skills-kit/backend-specialist)<a href="https://agentmods.dev/skills/lsantosweb/codex-agents-skills-kit/backend-specialist"><img src="https://agentmods.dev/badge/skills/lsantosweb/codex-agents-skills-kit/backend-specialist/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/lsantosweb/codex-agents-skills-kit/backend-specialist"><img src="https://agentmods.dev/badge/skills/lsantosweb/codex-agents-skills-kit/backend-specialist.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 | $0.00028 | $0.00401 |
| Opus 5.5 | $0.00011 | $0.00160 |
| Sonnet 5.5 | $0.00006 | $0.00080 |
| Haiku 4.5 | $0.00003 | $0.00040 |
Grade A, and why
backend-specialist 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.
What it actually says
When to use
Use this skill when the task involves:
- Node.js, Python, Bun, Hono, Fastify, Express, FastAPI, Django
- APIs, controllers, services, repositories, middleware
- auth, RBAC, JWT, sessions, OAuth
- backend integrations, queues, jobs, webhooks
- server-side bugs, validation, error handling, security
Core operating rules
- Clarify the runtime, framework, database, API style, auth model, and deployment target before coding when these are missing.
- Do not default to a favorite stack.
- Prefer clear layered architecture: controller → service → repository.
- Validate all input at the boundary.
- Do not expose internal errors to clients.
- Treat security as mandatory, not optional.
Decision guidance
- Edge/serverless Node: favor Hono.
- High-performance Node APIs: favor Fastify.
- Python async APIs: favor FastAPI.
- Broad public APIs: REST + OpenAPI.
- Internal TypeScript monorepos: consider tRPC.
- Simpler/local data needs: consider SQLite.
- Full relational workflows: favor PostgreSQL.
Execution workflow
- Restate the backend scope.
- Identify missing constraints.
- Propose the safest architecture choice.
- Implement in small diffs.
- Add or update validation, error handling, and security checks.
- Run relevant checks.
Mandatory checks
- No hardcoded secrets
- Input validation present
- Auth/authz applied where needed
- Consistent response shape
- Logging excludes sensitive data
- Relevant lint/type/test commands run
Output format
Report:
- what changed
- which files changed
- why the stack/architecture choice was made
- security and validation considerations
- checks run and results
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 · 60 lines · 28 tokens per session scan A 82cf97091f2e
backend-specialist is a skill published in the GitHub repository lsantosweb/codex-agents-skills-kit (2 stars, last pushed 7mo ago), licensed MIT. It adds 28 tokens to every session and 401 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.
backend-specialist compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| backend-specialistlsantosweb/codex-agents-skills-kit | Skill | 2 | 7mo ago | MIT | A | 28 | Codex |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 68k | 2d ago | Apache-2.0 | A | 217 | Claude Code, Codex |
| azure-mgmt-botservice-dotnetmicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 78 | Claude Code |
| fastapi-router-pymicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 46 | Claude Code |
| dev-runtimelangwatch/langwatch | Skill | 5.0k | yesterday | Apache-2.0 | A | 172 | Claude Code |
| api-designericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 105 | Claude Code, Codex |
| migrate-segw-to-raparc-mcp/arc-1 | Skill | 252 | yesterday | MIT | A | 106 | Claude Code |