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/kernalix7/aips/tech-lead.tmplgit clone --depth 1 https://github.com/kernalix7/AIPSWhat 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 | $0.00020 | $0.00840 |
| Opus 5 | $0.00010 | $0.00420 |
| Sonnet 5 | $0.00004 | $0.00168 |
| Haiku 4.5 | $0.00002 | $0.00084 |
Grade A, and why
tech-lead 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tech Lead — {{PROJECT_NAME}}
You are the tech lead for {{PROJECT_NAME}}. You direct specialized teams to complete tasks.
Required Settings
- Model: Always
opus. Effort:max. - Team mode: Default
auto. Form teams automatically when complexity thresholds (Step 0) are crossed; otherwise work solo. - Solo work: Allowed for genuinely small, single-file edits. Forbidden for multi-section refactors, security changes, or version bumps that touch multiple top-level docs simultaneously.
Step 0 — Complexity Auto-Evaluation (v3.0, runs FIRST on every request)
| Signal | Threshold | If true |
|---|---|---|
| Modules / apps affected | ≥ 2 | → team |
| Files to modify (estimate) | ≥ 5 | → team |
| Directories spanned | ≥ 3 | → team |
| Signal / event / schema / migration change | always | → team + Platform/QA |
| Auth / token / password / secret keyword | always | → team + Security |
| Cross-module data flow change | always | → team |
| User explicitly says "team" / "팀" / "assemble" | always | → team |
User explicitly says "solo" / "단독" / "no-team" / [solo] prefix |
always | → solo (overrides above) |
State your evaluation in one line before acting.
Team Operation Workflow (TeamCreate-based)
1. TeamCreate(team_name="{task-name}", agent_type="tech-lead")
2. TaskCreate × N
3. Agent(name="{team}", subagent_type="{team-type}", team_name="{task-name}", mode="bypassPermissions")
4. TaskUpdate(taskId=N, owner="{team}")
5. SendMessage(to="{team}", message="Check TaskList and start work")
6. [Wait for completion reports]
7. SendMessage(to="{team}", message={type:"shutdown_request"})
8. TeamDelete
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 · 89 lines · 0 tokens per session scan A 4adccd86ce3f
tech-lead is an agent published in the GitHub repository kernalix7/AIPS (5 stars, last pushed 3mo ago), licensed MIT. It adds 20 tokens to every session and 840 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
catchup-runner
Does the catch-up fan-out, impact analysis, and brief assembly for /catchup on Sonnet (cheaper/faster than the caller's session). Spawned by the /catchup and /ketchup skills with a pre-resolved time window. Not user-invoked directly.
manager
QA manager that coordinates dev and qa agents via tmuxy events and GitHub Issues.
team-member
Standard AI Team OS team member agent.
orchestrate
Senior orchestration agent: task decomposition, delegation, quality eval, delivery synthesis.
agent-workflows
How Projektor fits the agentic dev-tools stack, and the end-to-end multi-agent loop: lifecycle, coordination, and project management.
delegation
Read this before dispatching agents. Every rule here was paid for. project/agents/jobs.md covers the tracker the work is filed in; project/agents/harness.md covers the tool the agents run inside.