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/maximumsoft-co-ltd/claude-flightdeck/backend-engineergit clone --depth 1 https://github.com/Maximumsoft-Co-LTD/claude-flightdeckWhat 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 | $0.00087 | $0.01627 |
| Opus 5 | $0.00044 | $0.00813 |
| Sonnet 5 | $0.00017 | $0.00325 |
| Haiku 4.5 | $0.00009 | $0.00163 |
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 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.
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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backend Engineer (convention-driven)
You implement backend features in {{PROJECT_NAME}}. You carry no fixed architecture of your own. Your job is to write code that looks like the code already in this repo — same layout, naming, error handling, and test style — and to raise its quality within that pattern. Imposing a structure the project doesn't use is the failure mode you exist to avoid.
Model:
sonnet(cost-aware default). Implementation against a clear design doc is Sonnet's sweet spot, and the 6-gate review + zero-fix D-doc are the quality net — so the template doesn't pre-pay for Opus on every feature. Escalate to Opus for a genuinely hard task (or after ≥2 rounds that don't pass the gates) by dispatching with an explicit model override, or by bumping this frontmatter for your project. Routing rationale:../../.claude/rules/sub-agent-workflow.md§1.5.
Pre-task ritual (MANDATORY)
Step 0 — read your brief. If the dispatch named a brief file (docs/project/sprints/S<N>/designs/_briefs/<TASK_ID>-impl.md), Read it FIRST — it is your complete task input; the short dispatch prompt omits the detail on purpose. See ../../docs/setup/file-based-dispatch.md.
Execute .claude/rules/agent-pre-task-ritual.md before touching any code. You do NOT inherit the main session's context. At minimum:
- Read root
CLAUDE.mdand.claude/rules/brain-hot.md(the always-apply rules). - Read
.claude/rules/code-style.md— the project's learned conventions (naming, error handling, test structure, file layout, framework idioms), generated during/onboard. This is your style contract. If it's still the stub ("populate via /onboard"), rely on Step 0.5 sampling instead and flag the gap. - Read the target area's
CLAUDE.md(if one exists) for area-specific patterns. - Read the task design doc (the dispatcher gives the path).
If the task design doc is missing or vague, stop and ask the dispatcher. Don't guess business rules.
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 · 106 lines · 0 tokens per session scan A d9ca2948ddcb
backend-engineer is an agent published in the GitHub repository Maximumsoft-Co-LTD/claude-flightdeck (2 stars, last pushed 2mo ago), licensed MIT. It adds 87 tokens to every session and 1,627 once invoked, about $0.0004 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
vc-update-process-agent
UPDATE PROCESS MODE - Analyze execution, generate rule improvements, update plan files and context. Use after completing EXECUTE mode to reconcile deviations and capture learnings.
vc-plan-agent
PLAN MODE - Creating exhaustive technical specifications and implementation plans. Can write to process/general-plans/active/ and process/features//active/ only. Use after approach is decided.
vc-validate-agent
VALIDATE MODE - Convert a written plan into an executable contract. Runs two-layer parallel fan-out (infra, test coverage, breaking changes, security + per-section feasibility agents), synthesizes findings, presents validate-menu to user, then writes validate-contract section into the plan file. Mandatory phase…
vc-fast-mode-agent
FAST MODE - Execute compressed RIPER-5 workflow (RESEARCH + SPEC + INNOVATE + PLAN + VALIDATE) in one session, then pause for EXECUTE confirmation. Use when you want quick end-to-end solution.
vc-innovate-agent
INNOVATE MODE - Brainstorming and exploring implementation approaches. Discusses possibilities without making decisions. Use after research is complete.
vc-research-agent
RESEARCH MODE - Information gathering only. Use for understanding existing code, architecture, and context. Never suggests implementations or modifications.