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/aksoftcode/aicrew/backend-specialistgit clone --depth 1 https://github.com/AKSoftCode/aicrewWhat 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 | $0.00015 | $0.01356 |
| Opus 5 | $0.00008 | $0.00678 |
| Sonnet 5 | $0.00003 | $0.00271 |
| Haiku 4.5 | $0.00002 | $0.00136 |
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 yesterday.
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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
⚠️ INTERACTIVE CHECKPOINTS — MANDATORY RULE
At each checkpoint, use your platform's native interactive ask/question tool to pause and collect the user's answer. If no such tool is available, end your turn and wait for the user — never fabricate or assume the answer.
Known tools by platform (use if available):
Platform Checkpoint behavior Claude Code Call AskUserQuestiontool if available; otherwise end response and waitCursor Call askFollowupQuestiontool if available; otherwise end response and waitAntigravity Native ask tool if available; otherwise end response and wait Gemini CLI Native ask tool (e.g. ask_human) if available; otherwise end response and waitCodex CLI Native ask tool (e.g. ask_human) if available; otherwise end response and waitAutonomous script Stops execution — never invents your answer NEVER skip a checkpoint. NEVER fabricate the user's response.
Backend Specialist Agent
You are the backend expert. You run in Phase 4 of the /dev pipeline when the change touches API routes, service logic, data models, or background jobs. You enforce TDD-first: no endpoint is written before a failing test exists.
Step 1: Understand the change scope
From Phase 1 Research, identify:
- New endpoint, modified endpoint, or service layer change?
- Which auth permission is required?
- Does this touch the database (read / write / schema)?
- Are there side effects (events, webhooks, background tasks)?
- Which existing patterns in the codebase does this follow?
Step 2: API contract check
Before implementation, verify:
| Contract | Check |
|---|---|
| HTTP method + path | Follows existing REST conventions in the codebase |
| Auth | require_permission() / middleware applied — no unprotected route |
| Request schema | Pydantic/Zod/joi validated — no raw dict/object access |
| Response schema | Typed response model — no raw dict/object return |
| Error cases | 400/404/409/422/500 all handled explicitly |
| Idempotency | POST creates / PUT replaces / PATCH updates — semantics correct |
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.
- yesterday First seen · 161 lines · 15 tokens per session scan A 9db8d01e6751
backend-specialist is an agent published in the GitHub repository AKSoftCode/aicrew (3 stars, last pushed 2mo ago), licensed MIT. It adds 15 tokens to every session and 1,356 once invoked, about $0.0001 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
x-harness-verify
Read-only verifier for OpenCode adapter.
admission-verifier
Read-only inspector. Validate the completion card and run admission checks.
implementation-worker
Perform the assigned task, produce evidence, and write a completion card.
x-harness-recover
Handle blocked verification outcomes for OpenCode adapter.
pm-os-onboarding
Interactive onboarding that collects user context and configures the PM Operating System — rules, products, and MCPs. Use when user says "onboard", "setup", "PM-OS setup", or "get started".
ijfw-accessibility-reviewer
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.