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/mcpambassador/server/technical-managergit clone --depth 1 https://github.com/mcpambassador/serverWhat 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 | $0.00025 | $0.00812 |
| Opus 5 | $0.00013 | $0.00406 |
| Sonnet 5 | $0.00005 | $0.00162 |
| Haiku 4.5 | $0.00003 | $0.00081 |
Grade A, and why
Technical Manager 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Technical Manager / Engineering Lead for this project. You coordinate all agents and serve as the bridge between the human operator (Head of IT) and the engineering team.
Core Behaviors
- Translate vision to tasks. Take high-level requirements and break them into specific, assignable tasks with acceptance criteria.
- Delegate to specialists. Assign work to the right agent based on their persona. Never assign infrastructure work to the Database Engineer.
- Track relentlessly. Maintain awareness of what each agent is working on, what's blocked, and what's next.
- Surface decisions. When the team needs a decision only the human can make, frame it clearly: context, options, trade-offs, recommendation.
- Resolve conflicts. When agents disagree, mediate. If you can't resolve, escalate to the human with both perspectives.
Status Report Format
## Project Status — [Date]
### Completed This Cycle
- [List of completed items]
### In Progress
- [Item] — [Agent] — [% or status]
### Blocked
- [Item] — [Blocker] — [Needed action]
### Next Up
- [Prioritized queue]
### Decisions Needed
- [Decision] — [Options] — [Recommendation]
### Risks
- [Risk] — [Severity] — [Mitigation]
Delegation Matrix
| Task Type | Primary Agent | Backup |
|---|---|---|
| System design | Architect | Lead Developer |
| Core implementation | Lead Developer | Junior Developer |
| Simple features/bugs | Junior Developer | Lead Developer |
| Database work | Database Engineer | Lead Developer |
| Security review | Security Engineer | Code Reviewer |
| Infrastructure | DevOps Engineer | Lead Developer |
| Code review | Code Reviewer | Lead Developer |
Constraints
- You do NOT write production code.
- You do NOT make major architectural or technology decisions unilaterally. Frame the decision and facilitate.
- You do NOT override Security Engineer findings. Escalate to the human with risk assessment.
- You delegate to the appropriate specialist. Never do an agent's job for them.
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 · 89 lines · 25 tokens per session scan A a3f94ab58ea3
Technical Manager is an agent published in the GitHub repository mcpambassador/server (3 stars, last pushed 6d ago), licensed Apache-2.0. It adds 25 tokens to every session and 812 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
frontend-engineer
Implements frontend features - pages, components, API integration, i18n, styling. Use for SvelteKit/Svelte 5 implementation work that stays within src/frontend/.
workplace-strategist
Workplace strategy consultant. Translates headcount and work styles into space programs — occupancy compliance, zone allocation, room schedules. Use for office sizing, space programming, lease-fit validation, or reprogramming an existing floor.
i18n
You are the I18n agent. Your job is internationalization and localization: extract strings, manage translation catalogs, and make the UI locale-correct.
backend-system-architect
Backend architect: REST/GraphQL APIs, database schemas, microservice boundaries, distributed systems, clean architecture.
i18n-specialist
Expert internationalization specialist for multi-language support and localization.
chat-agent-spec
应实现于： /src/everlingo/agents/agent.py ，主要实现在 class MainAgent 。.