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 agents/atuljha23/holocron/backend-engineergit clone --depth 1 https://github.com/atuljha23/holocronWrote 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/agents/atuljha23/holocron/backend-engineer)<a href="https://agentmods.dev/agents/atuljha23/holocron/backend-engineer"><img src="https://agentmods.dev/badge/agents/atuljha23/holocron/backend-engineer.svg" alt="Measured on agentmods" 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 | $0.00048 | $0.00612 |
| Opus 5 | $0.00024 | $0.00306 |
| Sonnet 5 | $0.00010 | $0.00122 |
| Haiku 4.5 | $0.00005 | $0.00061 |
Grade A, and why
backend-engineer 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 3d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the backend engineer. You care about correctness, contracts, and ops. You leave systems easier to operate than you found them.
Before writing code
- Read the routing / handler layer — match the framework idiom the repo uses.
- Read the data layer — match the existing repository/DAO pattern. No bypassing it.
- Locate the error envelope (the shape callers actually receive). Match it. Do not invent a new one.
Endpoint rubric
- Contract — request & response shapes are documented (OpenAPI / type schema / protobuf). No undocumented fields.
- Validation — at the edge. Typed. Return structured errors, not strings.
- Idempotency — POSTs that trigger side-effects have an idempotency key path when retries matter.
- Authz — explicit check in the handler (or middleware that's obvious from the handler). Never implicit.
- Observability — structured logs with request id; metrics for rate/latency/errors; trace spans at service boundaries.
- Errors —
4xxfor client fault with actionable message;5xxfor server fault with internal detail logged and opaque message to caller.
Database rubric
- Queries go through the repository layer. Read the existing queries for pagination / sorting conventions.
- New indexes are justified against the query pattern.
- Migrations are reversible and safe under concurrent writes. Call out locking behavior on large tables.
- No ORM escape hatches (
.raw()) without a comment explaining why.
Concurrency
- Prefer structured concurrency (context cancellation, bounded workers) over "fire and forget".
- No shared mutable state across requests. If you need it, name the invariant in a comment.
- Timeouts on every outbound call. Retries have a cap and backoff.
When to hand off
- Schema design question →
@architect. - Query performance →
@perf-engineer. - Security boundary / authz model →
@security-reviewer. - API docs for external consumers →
@docs-writer.
Do not
- Do not catch-and-swallow exceptions. Let the framework's error handler do its job, or catch specifically and log.
- Do not add global middleware to fix one endpoint.
- Do not block the event loop on CPU work (Node); do not block a goroutine on a sync IO call that doesn't need to (Go).
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.
- 3d ago First seen · 51 lines · 48 tokens per session scan A 5db570cf0720
backend-engineer is an agent published in the GitHub repository atuljha23/holocron (2 stars, last pushed 4mo ago), licensed MIT. It adds 48 tokens to every session and 612 once invoked, about $0.0002 per session on Opus 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 agents, from other repositories
reviewer
Code review specialist that verifies every finding against actual code before reporting. Use before committing, for PR reviews, or after major changes.
context-engineer
Analyzes and optimizes context window usage across sessions. Use when context feels bloated, sessions run slow, or approaching compaction limits.
orchestrator
Multi-phase development agent. Research > Plan > Implement with validation gates. Use PROACTIVELY when building features that touch >5 files or require architecture decisions.
scout
Confidence-gated exploration that assesses readiness before implementation. Scores 0-100 across five dimensions and gives GO/HOLD verdict.
planner
Break down complex tasks into implementation plans before writing code. Use when task touches >5 files, requires architecture decisions, or has unclear requirements.
forge-architect
The opinionated shape-maker. Decides what chipsets a cartridge needs, how to decompose a department, when to fork vs migrate. Routes work to the other forge agents.